Chapter – 1 prepared by: D P Bhattarai

Definition and Nature of research

MEANING OF RESEARCH

Research means to search or study about a natural or social phenomenon. The term research is composed
by two different words “re” and “search” where “re” means repeatedly or again and again , and “ search “
means to investigate or find. Thus, to search again and again is research. Research is an effort to search a
new fact, knowledge and principle in scientific ways.

The nature of research conducted even in a common topic may vary considerably e.g. the research work
conducted to evaluate human development, history, religion, culture etc. is considered as social research.
This type of research is useful to examine human behavior, festivals, rituals, language, tradition etc. On
the other hand, the research work related to climate, environment, river, forest, planets etc. are widely
related to human beings but are not necessarily considered to be social research. Likewise, the research
works related to examine the chemical changes, physical changes, analysis of atoms and molecules etc. is
called scientific research. Similarly, the research work based on developmental activities made by human
beings like buildings, business activities, economic institutions, ornaments, equipments etc. are
considered as a part of business research. Thus, the research work in a common topic may be carried out
on the basis of available resources in different ways and consequently leads to different results.

Because of dynamic nature of society , the results of research in the same topic for a particular period of
time becomes false for other period due to the factors like education , urbanization , employment ,and
development in transportation and communication . For e.g. The response of individuals towards the
consumer goods produced by a factory, if observed excellent in a research may not necessarily remain
the same in other research works. The reasons for such results are different factors like taste, habit,
income, attitude, etc which are closely related to the individuals.

However scientific research is based on real and verifiable conclusion. Therefore, once verified or
examined results remain same for other time too. The social and business research lacks the valid
conclusions. Hence it is necessary to apply scientific methods of research in the same topic.

DEFINATION

Research is essentially a systematic inquiry seeking facts through objectives verifiable methods in order
to discover the relationship among them and to deduce from broad principles and laws. It is really a
method of critical thinking by defining and redefining problems, formulating hypothesis, collecting
organizing, evaluating data making deduction and making conclusions to determine whether they fit the
formulated hypothesis. Thus the term “ RESEARCH” refers to a critical and careful investigation or inquiry
having as its aim the revision of accepted conclusions in the light of newly discovered facts.

Some definitions of research have been mentioned as follows:

1
According to J.W.Best,”Research may be defined as the systematic and objective analysis and recording
of controlled observations that may lead to the developments of generalizations principles or theories,
resulting in prediction and possibly ultimate controls of events.”

Similarly Roger Bennett says “A systematic, careful inquiry or examination done to expand, verify
existing knowledge for some specific purpose is research .”

Another scholar sekaron says,” Research is a systematic and organized effort to investigate a specific
problem that needs a solution.”

On the basis of above mentioned definitions and explanations, it can be concluded that research is
………..

*directed towards the solutions of problems

*based on the observable experience or empirical evidence.

*demand accurate observations and description.

*involve gathering new data from primary sources or using existing data for a new purpose.

*require expertise and courage necessary to carryout investigation, search the related literatures and to
understand and analyze the data gathered.

*involves for question for answer to unsolved problems.

* able to predict something about the phenomenon.

CONCEPT, FEATURES AND PROCESS OF SCIENTIFIC RESEARCH

Any systematic and organized effort of investigation is known as scientific research .Scientific research
has the focused goal of problem solving and it applies a step-by-step logical and organized method to
identify problems, gather data, analyze the data and draw the valid conclusions from the available
evidences .Thus scientific research refers to a manner of doing research which is also known as scientific
method .To sum up, research has the following features :

*It relies on empirical evidences.

*It utilizes relevant concepts.

*It is committed to objectivity.

*It involves ethical neutrality.

*It describes the methodology used.

*It aims at formulating theories; etc.

2
According to F. N. Kerlinger there are eight steps in scientific research process which are more or less
common to all research methods and techniques:

(1)sensing or realizing the problems :- observations and sensing the problems is the first step of scientific
research process in which the researcher senses about the problem emerging in the
environment .Actually the researcher is not familiar about the problems but senses them in terms of what
,why and how is happening .

(2)Problem identification: - After having well awareness about the environment, the researcher focuses on
the problem and associated factors through further search of information. In this step, the problems
existing in the situation are identified and chosen for solution. Generally, there may exist various
problems under the selected environment and the researcher tries to select the vital problems upon which
the research work can be completed.

(3) Literature Review: - Review of literature means reviewing research studies or other relevant
propositions in the related area of the study so that all the past studies, their conclusions and weaknesses
may be known and further research can be conducted. A critical review of literature helps the researcher
to develop a deep understanding and insight into previous research works that relates to the present study.
It is also a way to avoid investigating problems that have already been definitely answered. Thus, the
review of literature accomplishes the following functions:

 It establishes a point of departure for future research

 It avoids needless duplication of costly research effort
 It reveals the areas needed research
 It provides methodology and guidelines to the researcher
 It saves time and expenditure of the research projects. Etc.
(4)Theoretical framework: - A theoretical framework attempts to integrate the information logically, so
that the reasons for the problem can be conceptualized. In this step, the critical variables are examined
and the association among them is identified. A theoretical framework is developed to put all the
variables and their associations together. It also focuses about the depth of subject matter under study.

(5) Hypothesis formulation: - Hypothesis means the tentative solution of the problem of research in hand.
Hypothesis formulation for the study is determined on the basis of theoretical framework. Sometimes,
prior assumptions about certain factor or statement are necessary and this type of statement is tested by
using suitable statistical tests.

(6) Research design:-The research design is the strategy for conducting research work, which describes
the general framework for collection, analysis and evaluation of identified data. It also describes the
methodology of research procedures.

(7) Collection of data: - Data collection is also called fieldwork, and it is the implementation of research
design .In this method the researcher applies the methods and instruments like questionnaires, schedules
interviews ,survey or sampling methods to gather data.

3
 (8) Data Analysis :- It involves the statistical analysis of collected ,edited, coded and tabulated data .The
validity of collected data is also tested by using different statistical methods such as a range , proportion
and percentage, mean mode median ,standard deviation , chi- square test and frequency distribution .

(9) Generalization: - The final step of scientific research process involves interpretation and
generalization of findings about the phenomenon. For the generalization of applied research, specific
implementation strategy is applied to solve the problem identified by the study.

BASIC AND APPLIED RESEARCH

A research can be undertaken for two purposes. The first is to generate a new knowledge in a particular
area and the other is to solve a currently existing problem. These are respectively termed as basic and
applied research. It means, research can be divided into two on the basis of its purpose such as basic and
applied. Detail description about basic and applied research is presented as follows:

 Basic research: - It is a search for broad principles and synthesis without any immediate utilization of
objective. It is not concerned with solving any practical problems and policies but with designing and
fashioning tools of analysis and with discovering universal laws and theories. Within this sense, P. V.
Young says “Gathering knowledge for knowledge’s sake is pure or basic research.” The main purpose of
conducting basic research is to search and advance the level of scientific knowledge, which is the genesis
of theory building. An example of basic research can be presented as follows:

The HRD managers commonly believe that on-the-job training has the great impact on the productivity
of the workers .However they have observed that the productivity of the workers over 45 years of age
does not improve from such training . Why is this so? What factors might be responsible for this
phenomenon? What type of training might be given to improve the productivity of such workers?

In such case, a researcher has to design an investigation and conduct a study observing on the job training
programs in different work settings and recording the effects of such trainings on the productivity of
younger and older workers.

 Applied research: - Applied research, also known as action research, is associated with a specific project
or problem. It is concerned to current activity or immediate practical situation. It is aimed at finding out
a solution for an immediate problem focused by a society .Applied research discovers what ,how and
why questions about policies ,programs ,and procedures of actual life .This type of research can be
conducted at any time whenever required to solve over the existing problems . An example of applied
research can be presented as follows:

The Janakpur cigarette factory has to improve its productivity in order to remain competitive in the
market. There are two alternative strategies to improve its productivity. One is to pay attention to all of
its existing brands and make continuous improvement; the other is to focus on new brand development.
Each of these alternatives has some advantages and disadvantages. The factory will now have to research
into each of these strategies and see which one would best suit the factory, taking into account its
capabilities, knowhow, resources and so on.

4
But applied research can become a case of blind leading the blind because of unduly localized research
report. The generalizations cannot acquire a universal validity. Because of these limitations, it may
produce wrong and unverifiable conclusions.

Difference between basic and applied research

Basic Applied
1. It aims to contribute at the theory and 1. It aims to solve or improve the problem.
techniques of the discipline.
2. It studies any problem usually from the 2. It studies problems with important social
focus of one discipline. consequences in several disciplines.
3. It requires mainly technical judgment. 3. It requires also a sense of what the situation and
personalities can be.
4. It restricts to research. 4. It is often useful in action or administration, not only in
research.
5. It seeks generalization. 5 .It studies individual cases without the objectives to
generalize.
6. It attempts to get all the facts. 6. It attempts only to correct facts.
Quantitative and qualitative paradigm of research
Quantitative research is applicable to the phenomena that can be expressed in terms of quantity or
amount. In other words quantitative research is based on the measurements like income, expenditure,
import, export prediction, population by age and so on. The results of quantitative research are purely
numeric. This research can present exact figure of the phenomenon. Generally, this method is very
popular in economics and business studies.

On the other hand, qualitative research is an approach to gathering and applying data using informal and
formal techniques of data collection and analysis. This research involves the exploration and
interpretation of the perceptions, opinion and behaviors of small samples of individuals. It is highly
focused, exploring in depth, the attitude of people. Qualitative research methods are taken from
sociology, anthropology and psychology. They provide examples and cases from the individuals, societies
and histories of human civilization. Qualitative research has been a major growth activity in management
over the past two decades. This design is particularly used in human resource and marketing research. It
provides powerful tools for research in these areas of management.

Difference between quantitative and qualitative research:-

Qualitative and quantitative methods are not simply different ways of doing same thing. Instead, they
have different strength and logics, and are often best used to address different questions and purposes.
These two types of research paradigms are differ in the following ways:

Quantitative research is useful in experimental and survey studies. The strength of qualitative research

lies in exploration and case studies.

5
 The researchers can use their judgments and opinions in qualitative research. Such judgments are,
however, not allowed in qualitative research.

 Quantitative research is involved when large sample is covered. On the other hand, qualitative research
typically studies a relatively smaller number of individuals and situations.

 There is breadth in quantitative research, and in qualitative research, there is depth.

 There is no fixed schedule of activities in qualitative research as compared to quantitative research.

FEATURES OF SOCIAL SCIENCE RESEARCH

 Social research is always directed toward the solution of problem.

 It is based on empirical or observable evidence.

 It gives emphasis to the development of theories, principles, and generalizations which are very
helpful in accurate prediction regarding the variables under study.

 It is characterized by systematic, objective and logical procedures.

 It is marked by patience, courage, and unhurried activities.

 It is replicable so that any person other than researcher him/herself may assess their validity.

 It uses either primary or secondary data as per requirement.

 It also uses the valid and scientific methodology of research.

But there are some difficulties of applying scientific method in social science research, and such
difficulties are as follows:

(1) Complexity of social events (dynamic nature of social events and changing human behavior).

(2)Heterogeneous socio-cultural practices.

(3) Intangibility of social events.

(4) Difficult to predict about the social phenomena.

(5) Qualitative feature of social events.

(6) Difficulties in the control and experiment of social events.

(7) Lack of universality of social events. Etc.

Beside these difficulties, a well trained and a qualified researcher can control and manage all the
difficulties using research ethics and modern methodology of scientific research.

6
 BUSINESS RESEARCH: CONCEPTS, TYPES, METHODOLOGY AND
VALUE OF DECISION MAKING
 CONCEPT:

Business sector has also been applying scientific research methodology to deal with the problems of
different sectors which arise during the operation of activities. A considerable number of management
problems can also be solved through management research. Similarly, research also enables the manager
to understand the internal and external environment which directly affects the operational activities. There
are mainly four functional areas of management such as- production, marketing, finance and human
resource management in which a manager has always to face with various practical problems and
management research helps to solve such problems. So, a brief description of research in different
functional areas has been presented as follows:

1. FINANCIAL MANAGEMENT RESEARCH:

It is usually concerned with:

*determination of financial needs of the enterprise

*raising funds at minimum cost

*making optimum allocation of funds in specific aspects.

*development of tools of control for evaluating the financial performance of the enterprise

*generation of financial data for decision making and their use in future

2.PRODUCTION MANAGEMENT RESEARCH

It focuses on technical aspects and is conducted to:

*identify new and better ways of producing goods

*invent modern technologies

*Reduce cost and improve product quality

3. HUMAN RESOURCE MANAGEMENT RESEARCH:

It includes the following:

*Organizational planning and development

*Training and development program for the employees

7
 *Age and salary administration

*Staffing, motivation, and recording of employee (it is the most difficult functional area due to the human
nature i.e. heredity and environment).

4. MARKETING MANAGEMENT RESEARCH:

It includes the following:

*Production and distribution of products

*Analysis of marketing institutions, marketing policies, and practices

*Planning of pricing, advertisement, and sale promotion

*Analysis of consumer’s behavior and interest.

DECISION MAKING IN MANAGEMENT RESEARCH

Nowadays, research has became a useful decision making tool for the professional managers. The
knowledge about research and the methods to be adopted at different disciplines are mostly similar. The
benefit of research knowledge to managers may help for identification of problem and amount of risk in
decision making.

Like scientific research process, there are different stages in management process which are limited to
the following four stages, such as:

(1)Analysis: - It is the initial stage in the management process in which attempts are made to recognize
opportunities and problems. In this stage, the decision maker is interested in understanding of the nature
and scope of a given problem that can be manageable through available resources.

(2) Planning: - It involves development and selection from alternatives as necessary course of action to
achieve an objective. It is an evaluation of plans and policies in order to predict the information under
study. It is a process which determines course of action, and guides for further decision making.

(3) Execution: - Generally, it is an output of an imagination (planning) focused by the decision makers
through relevant tools and techniques. In the broad sense, it is an implementation of analyzed and
planned programs in practice.

(4)Control: - It is the final stage of management research in which the performance against plans is
measured. Effective control is essential to achieve operational goals and objectives through effective
implementation plan.

These four phases of research in management area create a cyclic connection, so that the impact of one
phase becomes an overview of the other. Since, the decision making is involved at each of the above
stages and each stage has its own research needs.

TYPES AND METHODS OF MANAGEMENT RESEARCH

8
 There are mainly four types of management research which are as follows:

(1) Policy research: - The purpose of policy research is to support planning and decision making in forming
policies within the context of political, social, and economic realities of the time and setting. It is related
to the strategic analysis and planning activities of an organization.

(2) Managerial research: - It is related to the specific problem for which management has need of
additional information on which to base a decision (e.g. market potential for a new product, Etc.).

(3) Action research: - It involves a continuous gathering and analyzing of research data during the normal
on-going operations of an organization. It is designed to identify effective ways of dealing with
problems in the real world.

(4) Evaluation research: - This research is closely related with policy research in which policies,
objectives, strategies and programs are evaluated. Its real contribution lies on the fact that it helps
management to determine how far the programs have initiated by it been successful and also analyzes
the underlying cause of failure, if any.

METHODOLOGY FOR MANAGEMENT RESEARCH

(1) Policy research:

Objectives Data requirement Research output

*To formulate major policy Macro- level data (environmental *Identification of policy options
proposals forces, organizational situations)
*To establish their priorities *Identification of policy
*To identify their implications priorities for the organization,
etc.
(2) Managerial research

*To study the ongoing *Specific and detailed data about *Identification of the problem
operations or projects operations or projects situation
*To help in improving *Collection of qualitative data *Identification of decision
managerial efficiency options
*To help in decision making *Exploring the situation for in *Recommendation for action to
depth understanding be taken
*to improve the functioning of *continuous gathering and *to recommend the actions to be
organization analysis of data taken for: organizational
*to improve managerial actions *problem specific data (opinion structure, rules, reward and
*to suggest future courses of survey, observation, satisfaction punishment, performance
action level and frustration index) evaluation criteria, work
environment , etc.

(3) Action research

(4) Evaluation research:

9
 *to measure achievement against *micro- level data *identification of program
the objective strength and weaknesses
*to identify gaps and problem *internal surveys *recommendation for program
areas improvement.
*to suggest the improvements
required

BASIC REQUIREMENTS FOR A GOOD RESEARCH

 Purpose clearly defined

 Research process and work plan detailed

 Research design thoroughly planned

 High ethical standard applied

 Limitations frankly revealed

 Findings presented clearly without biasness

 Conclusions justified

 Researcher’s experience reflected, etc.

ETHICAL ISSUES IN MANAGEMENT RESEARCH

Ethical issues are critical aspects for the conduct of research. Ethics are moral principles or beliefs about
what is right or wrong. These beliefs guide researchers in their dealing with their respondents and other
related parties, and provide a basis for deciding whether behavior is right and proper.

Qualitative research is likely to lead to a greater range of ethical concerns in comparison with quantitative
research. However, all types of research methods have specific ethical issues associated with them.
Unethical behavior of research is thus a serious problem which is not easy to detect. Such behavior can
damage the credibility of the research findings and also of the institutions sponsoring the project.

Some common ethical issues that are likely to be found at different phases of research process are as
follows:

 Plagiarism (use of intellectual property without acknowledging him/her).

 Invasion of privacy (force the respondents to provide personal and confidential data).

 Fabrication and falsification of data for personal interest (replace actual data with false ones).

10
  Possible deception of participants (put pressure on the participants to grant access to
information).

 Dignity toward cultural and social norms and values.

 Non publication of data (the researcher should publish all types data except private information).

 Protecting rights of research participants (right to voluntary participation, right to anonymity,

right to well informed about research’s purpose, right to confidentiality and no participation at
the risk of harm).

Chapter 2

Preliminary stages of research

LITERATURE REVIEW

Review of literature means reviewing research studies or other relevant propositions in the related area of
the study so that all the past studies, their conclusions and weaknesses may be known and further research
can be conducted. It is an essential and basic process in research works. The main reason for a full review
of literature in the past is to know the outcomes of those investigations in areas where similar concepts
and methodologies had been used successfully. In this connection, a review of previous related research
findings will help the researcher to formulate a satisfactory structure for his/her research works.

Review of literature is an essential part of all studies. It is a way to discover what other research in the
area of our problem has uncovered. A critical review of literature helps the researcher to develop a deep
understanding and insight into previous research works that relates to the present study. It is also a way to
avoid investigating problems that have already been definitely answered. Thus, the review of literature
accomplishes the following functions:

 It establishes a point of departure for future research

 It avoids needless duplication of costly research effort
 It reveals the areas needed research
 It provides methodology and guidelines to the researcher
 It saves time and expenditure of the research projects. Etc.

Benefits of literature review

11
 i. Identification of research problem and relevant variables: - When the researcher makes a careful
review of literatures, he/she becomes aware of the important and unimportant variables in the
concerned area of a research. Thus, it helps the researcher to formulate a researchable problem in
which conceptually and practically important variables are selected.
ii. Avoidance of repetition: - It helps the researcher in avoiding any duplication of work done earlier. A
careful review always aims at interpreting prior studies and indicating their usefulness for the study to
be undertaken. Thus, prior studies serve as the foundation for the present study. But research works
are sometimes repeated which are needed to verify validity or reliability.
iii. Synthesis of prior works: - A careful review of literature enables the researcher to collect and
synthesize prior studies related to the present study. It also helps the researchers in building a better
perspective for future research and it also corrects the significant overlaps and gaps among the prior
works.
iv. Determining meaning and relationship among variables: - A careful review of literature enables the
researchers in discovering important variables relevant to the area of present research. When
significant variables are discovered, the relationship among them can be identified through which a
researcher can also formulate a workable hypothesis.
Sources of the literature

There are different sources of the review of literature, which are presented as follows:

i. Books and journals: - Different research journals and books relevant to the area of interest are the
primary sources of the literature review. Most major libraries have a periodical section where
different types of research journals are easily available. A research journal generally contains the
publications of original research reports with their detailed methodology and results. Similarly,
books are also direct sources of literature review which also provide basic knowledge of research.
ii. Reviews: - Reviews are short articles that provide brief information regarding the work done in a
particular area over a period of time. Reviews are commonly published in year books, hand books
and encyclopedia which are also beneficial to the researchers. These are mainly prepared by the
experts or reviewers.
iii. Abstracts: - The abstracts are the useful sources of up to date information for researchers. In an
abstract, researchers get all the relevant information such as title of the research report, name of
the author, journal pagination etc. regarding researchers who want to get methodology and results
of the research articles. These are also available in libraries and internet.
iv. Indexes: - Indexes show the title of the research report without any abstract. The titles are
categorized and arranged alphabetically so that a researcher can search the reports according to
his/her desire. Thus, the indexes can be best regarded as the supplementary source which, if
combines with sources, can yield valuable information to the researchers.
v. Dissertations: - The dissertations are also a very good source of the review of the literature and
these are available in university libraries. The researcher can choose the dissertations of their
interest and find useful chapters such as – literature survey, methodology, results and so on.

Phases in the review:

There are mainly four phases in the review of literature which are as follows:

I. First phase: selecting related literature after broad scan: Firstly, a superficial study of all relevant
literatures is done to develop a concept map which helps to formulate an idea and the selection of
working topics. Through such scanning a researcher can select a researchable topic and useful
literatures for the selection of relevant literatures, the following procedures can be applied:
 Identification of particular area through broad scanning for critical review.

12
  Carrying out a need assessment for the types of literatures sources (e.g. books, journals, news
papers, dissertations etc.)
 Determine the dates of publication of required literatures.
 Analyze the utility and relevance of the available literatures.
 Select the literatures for critical review.
II. Second Phase: - Preparing a working bibliography: - A researcher should prepare a working
bibliography card, through which he/she can easily search the relevant and useful literatures for
critical review. Such bibliography card should be made in sequential order or alphabetical order
for easy handling and managements. An example of bibliography card is presents as follows:

 Call No. of the books or Journals:

 Name of the author:
 Topic of the article/name of the book:
 Name of publisher, published place and date
 Name of the library where the literature is available:
 Brief description with content:

A bibliography Card:

Call Number 309.1

Y86 s
1998
Date of Author (Date of Birth/death)
Author’s name Kerlinger, F. N.
Title The Foundation of Behavioral Research
Place of Publication Bombay, Surjeet Publication.
Date of Publication Oct. 1978
Number of pages 816

III. Third Phase: Taking notes from source materials: - A researcher should have the ability of taking
notes from the source materials; otherwise, collection of information from the literatures will be
difficult. For this, a researcher can develop a format for note making which includes the
following items, and the size of the note card should be 4 ″ X 6″.Format for note making:

Title of the study: -

Authors: -
Publication year: -
Objective of the study:-
Problem statement/ hypothesis: -
Research method: -
Research findings: -
Conclusion: -

Before note making, a researcher should remember the following:

13
  Write the topic on the top of the card.
 Use different card for each idea, concepts and facts.
 Use quotation mark (“… .. .. …”) to mention the words of author.
 Mention the references (citation).

IV. Fourth Phase: - Critical review of literature: - critical reviews are written with either making
paragraph/paragraphs or without making paragraphs in one to four pages. Critical review writings
include the following sub topics:

 Introduction
 Summary
 Critique
 Conclusion
 Reference

Format of review presentation

There are no special criteria to develop a format for the presentation of review of literature. It means it is
presented in the form of paragraph as other writings. But there are some certain rules which a researcher
should follow compulsorily during the presentation of literature review. It is also called the citation
method; such rules are presented as follows:

 Extracts are chosen from the selected literatures.

 Time series of literature publication should be mentioned (ascending order)
 The extracts of the authors are arranged in alphabetical orders.
 All the problems should be highlighted in the extract.
 Only the author’s last name is written in the extract.
 Date of publication should be written in the bracket after the last name of the author etc.

Problem definition:

Problem definition is most important step in the research process. It is considered the most critical to the
success of the investigation. If the problem is stated vaguely or if the wrong problem is defined, then the
rest of research is completely useless. For example, is the problem faced by the company one of declining
sales or are declining sales merely a symptom of the real problem which could be poor product
development or inadequate advertising and sales promotions? Failure to have a proper definition of the
problem at hand can well invalidate the rest of the research study.

Sometimes, the researcher states the problem in terms of symptoms. If this happens, the study results
would be superficial. For example - Low productivity of workers may merely be symptoms of their skill
deficiencies. Under this condition, increase in incentive to workers will not improve productivity. Thus, it
should be recognized the correct problem to find out the correct solutions.

14
Techniques of defining research problems:

 Statement of the problem in general way

 Understanding the nature of the problem

 Surveying the available literatures
 Developing the ideas through discussions.
Some guidelines for selecting problems:

 A researcher should have deep interest toward a problem.

 It should neither too narrow nor too vague.
 Burning and immediate problems should be identified.
 Research problem should be important.
 It should not be controversial.
 It should be manageable on the basis of time and resources and availability of data.
 It should have practical implication.
Theoretical Framework:

A theoretical Framework is the basis or foundation upon which the study is established. It is within the
framework of the theory that the entire study proceeds. A theoretical framework is the foundation on
which the entire thesis is based. It is a logically developed, described and elaborated network of
associations among variables that have been identified through such process as interview, observation and
literature survey.

The preliminary survey of literature and information provides a solid foundation for developing a
theoretical framework. It describes the relationship among the variables, elaborates the theory underlying
these relations, and describes the nature and directions of the relationship. Thus, a good theoretical
framework provides the logical base for developing testable hypothesis; for example:-

Suppose, we have selected employee absenteeism as the dependent variable for our study. The
independent variables having effects on absenteeism could be age, sex, marital status and place of
residence of employees. We are using these four independent variables in an attempt to explain the
variance in employee absenteeism of an organization.

The grater the age of employees, the higher is likely to be the rate of absenteeism among them. The older
people have greater chances of sickness then the younger ones. Female employees tend to have higher
rate of absenteeism due to their family ties. Of the female employees too, married one demonstrate higher
rate of absenteeism then unmarried males and females. Due to their home ties and social links, the
employees coming from rural areas may have higher absences as compare to their urban counterparts.

On the basis of above arguments, we can theorize that there would be some co-relation between employee
absenteeism and each of the following variables: age, sex, marital status and place of residence of
employees.

Theory:

15
According to F. N. Kerlinger, “Theory is a set of interrelated constructs, definition and proposition that
present a systematic view of phenomena by specifying relation among variable with the purpose of
explaining and predicting the phenomena.”

Thus, a theory is a partially verified statement concerning the relationships among variables. The simplest
form of theory consists of two concepts joined by a proposed relationship. For example:-

“The more high-motivation in the employees, the more productivity of the

organization.” (Theory)

High motivation (concept – 1) Increasement in productivity

(concept – 2)

Proposition:
The term proposition denotes to the act of offering ( an idea ) for consideration; an idea or a plan offered;
a logical statement that affirms or denies something and is either true or false, in another sense, it is
suggestion: a proposal offered for acceptance or rejection. Proposition also helps a researcher in
formulation hypothesis. It means, it understands of researchable problem. For example- “The more the
incentive for work, the more productivity of the worker.”

Through such proposition, a researcher can formulate a testable hypothesis and other ideas of
further research.

Concepts and constructs:

Scientific research is based as concepts. A concept is an abstract symbol representing an object. It is a

property of an object or certain phenomenon. Concepts like democracy, commitment, participation,
leadership, social mobility etc. represent some meaning under one general name or label. Generally, these
concepts have accepted collection of meaning or characteristics associated with certain event, object,
condition, situation or behavior. Some concepts because of their frequent use have shared meaning and
usage. Others, which are less-used, do not have shared meaning. Thus, people may hold different
concepts of the same thing. Objects which can be seen, touched and felt are concrete concepts. Those,
which cannot be observed and felt, are abstract concepts. Their meaning and characteristics are coined
depending as the knowledge available in a society. As the knowledge increases, the meaning of these
abstract concepts may also change. In short, it can be said that concept is an understanding or perception
about an object or phenomenon.

16
 The abstract concepts are also called constructs. A construct is an image or idea specifically invented for
a given research. It means operationally defined concepts are the constructs. For example: motivation
related research can define the concept motivation as will-power (X 1) and willingness to work (X2) in
such cases, both will-power and willingness can be termed as constructs. In this way, the constructs need
to be translated into observable incidents or operation to produce empirical evidence.

Variables:

According to the dictionary of sociology, the term variable indicates to the characteristics or attributes
which are fixed for each person or other social entities, but which are observed to be at different levels,
amount or strength across samples and other aggregate groups. Variables measure a social construct such
as social class, age, occupations, religion or income etc. in a way which renders it measurable to
numerical analysis. Thus, a key feature of a variable is that it is capable of reflecting variation within a
population, and it is not a constant.

Defining the term variable, P. V. Young says “a variable is any quantity or characteristic which may
possess different numerical values or categories.”

Thus, variables are characteristics of persons, things, groups, objects etc. It is a symbol to which numerals
or values are assigned. For example – age, sex, occupation, productivity, job satisfaction, length of
service employee attitude etc.

Types of variables

There are three types of variables, such as:

1. Independent variables: - The variables which are not depended upon other variables are called
independent variables. For e.g. –two variables such as on the job training and efficiency of employee, the
former is considered as independent variable. In other words, when there is cause- effect relationship in
an event, in such case, cause is considered as independent variable and effect is considered as dependent
variable; such as:

Smoking

(independent variable) Lung cancer

(dependent variable)

2. Dependent variable: - The variables which are dependent upon other variables are called dependent
variables. Such as:

Advertisement Sale promotion

17
 on the job training Increasing efficiency

(Independent) (Dependent)

3. Intervening variables:- The variables which directly affect the dependent variables are called the
intervening variables; for example:
(Independent) (Dependent)

Training Efficiency

Age group

>50&<50

Wage job satisfaction

Extra income

(Intervening variables)

Deductive and Inductive Reasoning

1) Deduction: - Deduction is just opposite to induction method and it is a process of reasoning from
general principles to particular instances. Deduction is used in scientific method when specific
hypothesis or particular predictions are derived from broader theoretical principles. It means, it is a
scientific method of inquiry from general to particular. The main task of deductive logic is to clarify
the nature of relation between general assumptions and conclusions with valid arguments. It is
concerned with the working out of logical implications between propositions. Let us take an
example:
- All men are mortal (theory)
- Hari is a man (hypothesis)
- Hari is mortal (conclusion/ generalization)

18
Here, the conclusion follows from the two assumptions logically, therefore it is valid. So, it is also called
the method of intellectual experiment or hypothesis testing. But sometimes it becomes the intellectual doll
if there is error in general truth or some errors in propositions; for example:

-Some men are honest

- Hari is a man

- So, Hari is honest

However, it is very common method of scientific investigation and frequently applied in social and
management research. It has the following merits and demerits:

Merits:

 It is simple and easy method, which is not time consuming and expensive.
 This method leads to accuracy in generalization, because, it uses logic and mathematical tools of
analysis.
 It is more useful in quantitative research.
Demerits:

 It is also harmful if the researcher uses the propositions which are incorrect or partially correct.
 Sometimes, the conclusions drawn from deductive analysis may be far from reality.
 It needs high expertise and skills for deductive analysis.

2) Induction:
It is an important approach of research for theory building. Generally production of facts
to prove general statement informing of general law from particular instances is called induction
method. The dictionary of sociology defines this term as “The logical process in which
generalizations are inferred from specific facts. Essentially, induction is the process of reasoning
from individual instances to general principles.” The experimental method is basically inductive,
in that, general conclusions are derived from individual observations.

So, induction is a process of reasoning whereby we arrive at universal generalizations and

it is opposite to deduction. It involves two processes, such as: observation and generalization. In a
number of cases, it is observed that educated girls have expensive habit; one may conclude that
all educated girls have expensive habit. This is the simplest kind of induction, and it is called
induction by enumeration. However, scientific induction is based on known causal connection.
Induction by enumeration gives us only probable conclusion, but scientific induction gives us
certain conclusions.

# Merits of induction:

 It is based on observed facts and realistic foundation, and they are precise and accurate.
 It is scientific in character, some of the important theories of physical and social sciences
have been developed through this method.
 It supplies the universal premise and it is also helpful in finding out material truth.
# Demerits of Induction:

19
  It is time consuming, expensive, and complicated method.
 It is a complex job; an investigator using this method requires a high degree of
competence and training, beside sophisticated tools of analysis.
 It often leads to hurried and wrong generalization.
 It sometimes produces only a mass of unrelated and unconnected facts.
Research question

The research question indicates the purpose and motive of the researcher and this is the vital component
of a research study. It means what the researcher specially wants to understand by doing the study? The
researcher should clearly spell out what he/she will attempt to learn or understand. The intentions of
researcher are expressed in the form of research questions. The research questions are directly linked to
all the other components of the research investigation.

The research question has the following functions:

 To help the researcher to focus the study (the questions’ relationship to the research purpose and
conceptual context).
 To give the researcher guidance on how to conduct it (their relationship to methods and validity).
Beside these, a research question helps a researcher in the following aspects:

 Choice of informants
 Method of data collection
 Tools and techniques of data analysis
 Decision for conducting research.
Hypothesis Formulation

The term hypothesis is a union of two words – “hypo” and “thesis”. Literally, ‘hypo’ means
under or below and ‘thesis’ means a reasoned theory or rational viewpoint. Thus, hypothesis would mean
a theory which is not fully reasoned. In other words, hypothesis is a theory entertained in order to study
the facts and examine the validity of the theory.

According to Webster, “A hypothesis is a proposition, condition or principle which is assumed,

perhaps without belief, in order to draw out its logical consequence, and by this method to test its
relevance with facts which are known or may be determined.”

Lundberg says, “A hypothesis is a tentative generalization or justification, the validity of which

remains to be tested”.

Likewise, Rummel and Balline says, “A hypothesis is a statement capable of being tested and
thereby verified or rejected”.

These definitions suggest that a hypothesis is a provisional formulation or possible solution, or

tentative explanation or suggested answer to the problems facing by the researcher. It is an explanation
that needs to be established before it can be accepted. If the hypothesis is proved, the tentative solution of
the problem is answered and if not so, alternative solution would need to be formulated and tested. Thus,
a hypothesis stands somewhere at the midpoint of research from which one can look back to the problem
and also look forward to the data.

20
 Research problem, theory and hypothesis are closely related to each other. For this, the method of
induction and deduction are applied through which a workable hypothesis can be formulated, for
example:

 Problem: Nepal’s population is increasing so rapidly that if it is continued at its present rate in 30
years, it will not be possible to feed all of its citizens.
 Theory: Population growth can be controlled through family planning clinics.
 Hypothesis: Family planning can reduce the growth of population in Nepal.
Functions of hypothesis:

 Adequate explanation of all facts connected with the hypothesis.

 It helps to collect necessary evidence in order to discover the order of nature.
 It leads to the discovery of laws and seeks to verify knowledge.
 It limits the scope of inquiry to manageable area (time, money, data etc.).
Types and format of hypothesis:

Hypotheses are of two types, which are:

 Alternative hypothesis: - It is also called the research hypothesis which states the expectations of
the researcher in positive terms. It defines the variables for conditions, which, in causal
relationship, will be advanced, to account for the results and is often derived from theory.
Statistically, it has given the symbol as:
H1 or HA. . It is a statement expressing a relationship between two variables or indicating
differences between groups, for example:

H1: Male workers will have more productivity than female workers, or,

Female workers will have less productivity than male workers.

Statistically expressed: H1: u1>u2

Where,

H1= Alternative hypothesis

U1= productivity of male workers

U2= productivity of female workers

 Null hypothesis: - It indicates a definite and exact relationship between two variables. That is, it
states that the population correlation between two variables is equal to zero. It is called the ‘Null’
because it usually reflects the ‘no’ difference or ‘no effect’ situation. Symbolically it is expressed
as: Ho , For example:
Ho : There is no difference between male and female in their productivity.

Statistically expressed: Ho: U1=U2 / Ho: U1 – U2 =0

Where,

Ho = Null hypothesis

21
 U1 = Productivity of male workers

U2 = Productivity of female workers

Formats of hypothesis

According to Knowles, there are 3 different formats of hypothesis construction based on

association and correlation between variables, such as:

Correlation:

 There is significant relationship between variable A, and B for group- 1

 There is significant relationship for group – 1 among all the variables (var. A, B & C)
 There is significant relationship in group 1, 2, and 3 among all the variables (var. A, B, C etc.)
Difference between means:

 There is significant difference between mean levels of variable A for group 1 & 2
 There is significant difference between means for group 1 and 2 in terms of variables a, B, & C.
 There is significant difference between means for group 1, 2, & 3 in terms of variables a, B, & C.
Difference between frequencies:

 There is significant difference between group 1 & 2 for variable A

 There is significant difference between group 1, 2, & 3 for the variable a, B & C.
Features and criteria of good hypothesis:

 A hypothesis must be conceptually clear,

 A hypothesis should be empirically verifiable,
 A hypothesis must be specific,
 A hypothesis should be related to available techniques,
 It should be related to a body of theory,
 It should be simple,
 It should be logically consistent,
 Variables of hypothesis must be definable, interrelated and measurable.

Chapter - 3

RESEARCH DESIGN

Concept of research design

A research design means an overall framework or plan for the activities to be undertaken during the
course of a research study. The research design serves as a framework for the study, guiding the
collection and analysis of data, the research instruments to be utilized, and the sampling plan to be
followed. Specifically speaking, research design describes the general plan for collecting, analyzing, and
evaluating data after identifying the following:

 What the researcher wants to know?

 What has to be dealt with in order to obtain the required information?

22
According to Paul, E. Green and Donald, S. Tull, “ A research design is the specification of methods and
procedures for acquiring the information needed. It is the overall operational pattern of framework of the
project that stipulates what information is to be collected from which resource and by what procedures. If
it is a good design, it will ensure that the information obtained is relevant to the research questions and
that it was collected by economical and procedures.”

Thus, a research design is a plan for the collection and analysis of data. It presents a series of guide posts
to enable the researcher to progress in the right direction in order to achieve the goal. Generally, a
common research design possesses the five basic elements such as – (i) selection of problem (ii)
methodology (iii) data collection (iv) data analysis (v) report writing.

Research design has mainly two purposes, such as :

- To provide answers to research questions,

- To control variance. (unnecessary and intervening variables can be controlled)
Thus, it can be said that research design is a framework or a general plan for the study guiding the
collection and analysis of data. It focuses as the data collection methods, the research instruments utilized
and the sampling plan to be used. It is an integrated approach that guides the researcher in formulating,
implementing and controlling the study. The basic elements of a research design are : (i) the problem, (ii)
the methodology, (iii) data gathering (iv) data analysis and report writing. A good research design
combines all these elements.

# Classification of research Design:-

1. Exploratory design:- It is a type of research concerned with discovering the general nature of a
problem and the factors that relate to it. Generally, this research design is applied to study about
completely new problem or event. It gives high emphasis as the collection of evidence rather than the
description of the phenomenon. It is also called formulative research design which relies on empirical
evidence; and utilize relevant concepts. It is committed to objectivity, applies ethical neutrality,
describes the methodology used and it is also helpful to formulate new theory. This research design is
based as the following three methods:
- Review of relevant surveys,
- Empirical survey,
- Case study of the event.
This method has frequently been using to solve the problems related to the management areas by
the modern researchers.

(2) Historical Research Design:- Historical research is concerned with past phenomenon. It is
a process of collecting , evaluating, verifying and synthesizing past evidence systematically and
objectively to reach a conclusion. It may also attempt to understand the trends in the past and
reconstruct the origin and development of those events. The main purpose of conducting
historical research is to show the relevance of past events to the present.Accuracy of gathered
information is the main consideration of success in historical research. Both primary and
secondary data are used in this research. It is unique among the various types of research in that
the sources of data being studied are usually not available for the researcher’s direct observation.
Steps of historical research:

(i) Define the problem (ask yourselves these questions: Is the historical approach best suited for
this problem ? Are relevant date available ? Will the findings be significant ?

23
 (ii) Statement of research objective (If possible, state the hypothesis ).
(iii) Collection of date (through note taking)
(iv) Evaluation of date (applying both internal and external criticism)
(v) Report writing (details from introduction to bibliography)
(3)Descriptive research design:- It is a fact finding operation searching for adequate information. It is a type
of study, which is generally conducted to assess the opinions, behaviors or characteristics of a given
population and to describe the situation and events occurring at presents. It is a process of a cumulating
facts. It does not necessarily seek to explain relationship test hypothesis, make predictions or get at
meanings and implications of a study. Hence, a descriptive research is an extension of an exploratory
research.
Although descriptive research cannot predict and control condition and events, it contributes to
science primarily by building a foundation of facts upon which exploratory hypothesis may be
constructed, by checking the validity of existing theory and by directing attention toward alternative
hypotheses which better fit the facts.

Steps in descriptive research :-

(i) Define the objectives ( in clear, specific terms that what facts and characteristics are to be
uncovered )
(ii) Design the approach (date collection and analysis methods)
(iii) Collect the data.
(iv) Report the results.

4. Case Study Research Design:-

A case study is a fairly intensive examination of a single unit such as – a person, a family, an institution, a
commodity, a district or any single event. It is an approach, which views any social unit as whole. It is a
way or organizing social data so as to preserve the unitary character of the social object. A case study
enables a researcher to explore and understand problems, issues and relationships in a particular situation.
However, it can not allow us to generalize our research i.e. to argue the findings, results or theories from
one case study to other case studies. But if we consider a number of case studies in combination, it may
facilitate to develop a theory as generalization. A case study method is extensively used in psychology,
education, economics, sociology and business research particularly in the field of marketing, management
and personnel. The source of data through interview, exploratory observation, personal documents, life
history etc.

Steps in Case study:-

 State the objectives (what is the unit of study and what characteristics, relationships and processes
will direct the investigation ?)
 Design the approach (how will the units be selected ? what sources and methods of data
collection will be used ?)
 Collect the data
 Organize the information (analysis)
 Report the results and discuss their significance.
(4) Developmental Research Design:-

24
Development research is conducted for the purpose of predicting further trends. It concentrates on the
study of variables, their rates of change, directions, sequences and other interrelated factors over a period
of time. Developmental research may be conducted in the following three ways:

(a) Longitudinal growth study:- It measures the nature and rate of change in a sample at different
stages of development. This occurs when the data are collected at two or more points in time
from the same group of individuals.
(b) Cross-sectional growth study:- It measures the rates of changes by drawing samples from a cross-
section of society. This study focuses as comparing and describing groups. In this study, data are
gathered just once, perhaps over a period of time, in order to answer research question. Such
studies are also known as one-shot studies.
(c) Trend study:- It is designed to study the patterns of change in the past in order to predict future
conditions. When the data are collected at intervals spread over a period of time, it is called a
trend study. Trend studies are sued to obtain and analyze social, economic and political data to
identify trends and to predict what is likely to take place in the future.

Steps in developmental studies:-

 Defining the problem/statement of objectives.

 Literature review
 Data collection
 Evaluation and analysis of data
 Interpretation/ report writing
6. Co-relational Research Design:-Correlation research is concerned to ascertain the extent of
relationship between the phenomena under investigation. It describes the association (relationship)
between the variables. The relation between two or more variables may be high, moderate, or low degree
according to the relationship that depend strongly, moderately or poorly respectively.

In correlation research, the researcher’s main interest is to determine whether two or more variables co-
vary, and if so , to establish the direction, magnitude and form of the observed relationship. Variables thus
may be closely related, moderately related or completely unrelated. There are three types of correlations:

(a) Positive correlation:- It exists when an increase in one variable is accompanied by an increase in
another. For example- increase in benefits to workers increases productivity.
(b) Negative correlation:- It exists when two variables are negatively related. An increase in one
variable would result in decrease in another. For example – an increase in absence rate of
employees could result in decrease in production.
(c) No correlation:- It exists if any change in one variable does not affect other variables, such case is
called no correlation between the variables.
Steps in correlation research:

 Define the problem

 Review the literature

25
  Design the approach (identify the relevant variables and select the correlation approach that fits
the problem)
 Collect the data
 Analyze and interpret the results.

(VII) Causal comparative research design:

Causal comparative research is also called regression research method that investigates the possible
causes affecting a particular situation by observing existing consequences and searching for the possible
factors leading to these results. This design also predicts the dependent variable on the basis of
independent variables. The cause is also manipulated to measure the effect in various ways. In this design,
the researcher searches the similarities and differences among the selected topic to obtain clues about
what might cause or contribute to the occurrence of a particular phenomenon. It is similar to ex-post facto
in nature.

This design involves the following steps:

 Formulation of the problem

 Statement of hypothesis
 Date collection
 Analysis and generalization
 Interpretation

(VIII) Survey Research Design:-

The term survey has two words ‘sur’ and ‘veir’ which mean ‘over’ and ‘see’ respectively. So, the term
survey means to look over or to oversee, i.e. to look-over something from a high place. In social science,
it indicates the investigation of social problems the technique of collection of data through interview,
questionnaire, library or books.

Surveys are conducted in case of descriptive research studies which have larger samples. The survey
method gathers data from a relatively large number of cases at a particular time, so, it is essentially cross-
sectional. Surveys are usually appropriate in case of social and behavioral sciences. They are examples of
field research. It is concerned with hypothesis formulation and testing the analysis of the relationship
between non-manipulated variables. Surveys may be census or sample surveys. The method of date
collection happens to be either observation, interviews, questionnaire or same projective techniques.

Types of Survey:

(I) Regular and ad-hoc.

(II) Census or sample survey
(III) Primary or secondary
(IV) Initial or repetitive survey
(V) Official, semi-official or private
(VI) Widespread or limited survey
(VII) Public or confidential survey
(VIII) Base-line and evaluation survey

26
Steps in Survey:-

 Problem identification
 Planning for survey
 Determination of methodology and hypothesis
 Data collection
 Report writing

(IX) Experimental Research Design:-

This method is generally applied in physical sciences because true experimental research design is not
applicable in social science and management research. Experimental research starts with the identification
and analysis of a problem. The issues involved are sharpened by formulating hypothesis and deducting
the consequences. A hypothesis suggests that an independent variable (x) is related to the occurrence of
another condition, event or effect (dependent variable Y). To test a hypothesis, a researcher controls all
conditions except the independent variable, which he/she manipulates. Then he/she observes what
happens to the dependent variable. The dependent variable is the phenomena that appears, disappears or
changes as the researcher applies, removes or varies the independent variable. The independent variable is
manipulated under observation to ascertain its relationships with the dependent variable.

A botanist, for example, can contend that sunlight (independent variable) has an effect on plant growth
(dependent variable). To test this hypothesis, he/she would obtain plants of the same species, cover each
with a bell-jar and place one in a shaded place and the other in sunlight. Thus, he/she manipulated the
amount of sunlight the plant receives. His/her experiment will give him/her direct empirical evidence that
exposure to the sun results in plant growth and absence of sunlight retards plant growth.

Steps:

 Identify and define the problem

 Survey the literature

 State hypothesis
 Construct an experimental plan
 Conduct the experiment
 Take observation for data collection
 Apply an appropriate test of significance to reach in to a conclusion.

(X) Quasi-experimental research design:-

Considering the limitations in applying strictly controlled experimental research in social sciences, the
quasi-experimental research design has been suggested. The purpose of this research is to approximate the
conditions of the true experiment in a setting which does not allow the control and manipulation of all
relevant variables.

In a quasi-experimental study, at least one characteristic of a true experiment is missing, either

randomization or the use of a separate control group. A quasi-experimental study, however always
includes manipulation of an independent variable that serves as an intervention.

27
One of the most common quasi-experimental design uses two (or more) groups, one of which serves a
control group in which no intervention takes place but groups are observed before as well as after the
intervention, to test if the intervention has made any difference. The subjects in the two groups (study and
control groups) have not been randomly assigned; for e.g.

Study group (before) ….. intervention ….. study group (after)……

Compare

Control group (before) …… ………………… Control group (after) ………

Steps:-

 Identify and define problems

 Survey the literature
 State hypothesis
 Construct a quasi-experimental plan
 Conduct the quasi-experimental study
 Take observations for data collection
 Apply an appropriate test of significance to reach in to a conclusion.

PILOT STUDY:-

A pilot study is a preliminary study conducted on a limited scale before the original studies are carried out
in order to gain some primary information, on the basis of which the main project would be planned and
formulated. The main objective of pilot study is to test the validity of questionnaire or interview schedule.
Pilot study is undertaken without formulating any hypothesis about the problem. It is made on a small
sample, which represents the true population (generally two to five percent sample). During interview it is
easy to identify the contents of schedule or questionnaire in terms of meaning, embarrassing area of
inquiry, respondents’ reaction and learn if any should be rearranged, removed or added. The schedule or
questionnaire prepared after the pilot study will be more practical and perfect for the researchers through
which he/she can gather actual and required information. The pilot study helps to clarify many of the
problems left unsolved by previous tests. The size and design of the pilot study is a matter of
convenience, time and money. Specially, a pilot study provides guidance of the following:

 Estimating the cost and duration of the main survey

 The suitability of the method of data collection
 The expected non-response rate

28
  The adequacy of questionnaire, accuracy, efficiency and clarity, the kind of interviewers and
respondents.
 The efficiency of the instructions and general briefing of interviewers.
 The adequacy of the sampling frame from which it is proposed to select the sample.
 The efficiency of the organization in the field, in the office and in the communication between the
two.

Sources of errors in research design:

There are some certain errors in research design and such errors should be avoided or minimized by the
researchers otherwise, such errors lead to false conclusion. Some frequently observed sources of errors in
research design are as follows:
i. Poor research formulation
ii. Selection of improper research design
iii. Poor data collection methods
iv. Poor logic
v. Inadequate sample design
vi. Inappropriate statistical procedures
vii. Other shortcomings.
According to Isaac, such errors are technically expressed as:
(1) The Halo effect: - Negative or positive impression to the researcher during observation (first
impression always leads to some strong conclusion). For this, related variables should be clearly
defined.
(2) Rating error: -
(a) Over rater error: - sometimes the respondents provide information more than the actual
situation.
(b) Under rater error: - Sometimes the respondents provide information less than actual
situation.
(c) The central error: - sometimes questions are designed differently ‘yes’ or ‘no’ options. In
such case, the respondent has no other choice which leads to errors.

Chapter - iv
MEASUREMENT AND SCALING
Concept and importance of measurement:
A measurement procedure consists of the techniques for collecting valid, reliable and precise data through
different sources. It means, measurement is the assignment of numerals to objects or events according to
rules. Thus, measurement is a value which reflects the presence of some characteristics. A numeral is a
symbol of the form; 1, 2, 3 …….. or I, III, III etc. It has no quantitative meaning. It is simply a symbol of
special kind. It can be used to label objects such as volleyball players, workers, students, or individuals
drawn in a sample from a universe.
Measurement is a relatively complex and demanding task especially when it concerns qualitative
or abstract phenomena. By measurement, we mean the process of assigning numbers to objects or
observations, the levels of measurement being a function of the rule under which the numbers are
assigned. So, technically speaking, measurement is a process of mapping or assignment of symbols or
numbers to the objects or events by the researcher for the collected facts. For example, if a researcher
wants to know the marital status of people in his observation, then he may give different symbols to
unmarried, married, widowed or divorced as 1, 2, 3, & 4 respectively and for male and female as A & B
etc. Another example:

Marks obtained in Research measurement

29
 30 - 40 1
40 - 50 2
50 - 60 3
60 - 70 4
The process of measurement may range from the simple tabulation to the use of complex
statistical procedures for the number of cases and categories. Thus, measurement technique is very
important in social science and behavioral research. It means, without measurement, the research process
will be in complete.
Data types/Types of measurement:-
In social science and management research, there are four basic types of measurement or scales
such as: nominal, ordinal, interval and ratio. The data collected for the research study will fit into one of
these four scales. It is therefore important to understand the different levels of data to do a proper
analysis. A brief description and examples of each category of measurement scales has been presented as
follows:

(i) Nominal scale:- A nominal scale is one that allows the researcher to assign subjects to certain
categories or groups. This is the simplest and lowest form of data and it gives very basic
information. This scale is usually used to obtain personal data, where grouping of individuals or
objects is required. For example:
Gender - Male, Female
Religion - Hindu, Buddhist, Muslim, Christian
Occupation - Teacher, Manager, doctor, businessman, Civil service
Nationality - Nepali, Indian, American, Japanese
Department - Sales, Finance, Personnel, Production

All categories are mutually exclusive. Every respondent has to fit into one of these categories.
Therefore, one cannot rank these and say that a male is a higher value then a female or that a
teacher is a high value then a manager. Thus, nominal scale tells us nothing more than basic or
gross information.

(ii) Ordinal scale:- This scale is usually used to rate the preferences of the respondents. This scale
applies to data which can be ranked according to value but cannot be given a particular numerical
value which actually is descriptive of the data. For example one can rank drinks ( alcohol,
cocacola, tea, coffee, soda, water, mineral water ) in order of his or her preference from most
preferred to least preferred. Another example can be presented as follows:

Rank the following cities in terms of their suitability to open a branch office:
Cities Rank

Biratnagar ----
Hetauda ----
Janakpur ----
Butwal ----
Nepalganj ----
Dhangadi ----
Bharatpur ----

30
 Ordinal scales represent numbers, letters, or any symbols used to rank items. The significant
amount of business research relies as ordinal measures. The most common usage of ordinal scale
is in obtaining preference measurement.
(iii) Interval Scale:- this scale assumes that the data have equal differences or intervals. Interval scale
posses the characteristics of nominal and ordinal scales. Especially the rank order characteristics.
In addition, numerically equal distances an interval scales represent equal distances in the
properly being measured. For example we measure 4 objects on an interval scale and get the
values 8, 6, 5 & 3. Then we can logically say that the differences between first and third objects
in the property measured, 8-5 = 3 is equal to the difference between second and fourth objects 6-3
= 3. Another way to express the equal interval idea is to say that the intervals can be added and
subtracted; an interval scale is assumed as follows:

A B C D E
1 2 3 4 5

Here, the interval from A to C or B to D or C to E is same ( 3-1 = 2, 4-2 = 2, 5-3 = 2). So, such
type of scaling is called the interval scale.
(iv) Ratio scale:- The ratio scale is the most powerful of the four scales because it has an absolute
zero origin and consists all the properties of the other three scales. This allows the researcher to
calculate the ratio difference between the age, income, working hour etc. of the individuals. For
example, we can say that a man who is 40 years old is twice as old as the man who is 20 years
old. Ratio scales are found more commonly in the physical science than in the social sciences.
Measurement of weight, length, time, intervals, area, velocity etc. All conform to ratio scales. In
social science, we do find properties of concern that can be ratio scales: money, age, working
hour, years of education etc. However, successful ratio scaling of behavioral attributes is rare.
The scale and measurement can be compared considering a question regarding income, for
example:

Ordinal Interval Ratio

What is your income? What is your income? What is your income?
Very low Less than Rs. 1000 My monthly
Low Rs. 1000 – 2000 income is
Average Rs. 2000 - 3000 Rs. …. … ..
High Rs. 3000 – 4000
Very high Rs. 4000 +

Attitude measurement: concept & Techniques:-

People have certain feelings, perceptions and behavior toward other things, people, places and
times. These feelings and perceptions are called attitudes and social scientists frequently desire to know
people’s attitudes. These are measured by attitude scales, it is because the above mentioned nominal,
ordinal, interval and ratio scales cannot measure people’s attitude. So that, attitude scales have been
developed by different social scientists to measure people’s attitude. People’s feelings, attitudes, likes and
dislikes, agreement and disagreement etc. can be measured by this method. So, it is quite popular in
sociology, psychology, education, marketing and personal management. There are some well-known
scales of attitude measurement which are presented as follows:

(i) Arbitrary Scales:- These scales are developed on an arbitrary basis. These are designed
largely through the researcher’s own subjective selection of items. The following
example illustrates the arbitrary selection of items:

31
Example : how do you assess the reputation of this college?

As a place of excellent facilities……… bad…………..good

As a place of excellent learning bad……………good
As a place of promoting creativity bad……….good
As a place of interdisciplinary interaction bad………..good
The main advantage of this scale construction is that it can be developed quite easily, quickly
with relatively less expenses. They can be designed to be highly specific and adequate. Because
of these benefits, such scales are widely used in practice.
(ii) Summated rating scales/ Likert type scale:
This is a self – report technique for attitude measurement in which the subjects are asked
to indicate their degree of agreement or disagreement with each of a number of
statements. A subject’s attitude score is the total obtained by summing over the items in
the scale. This is a summated scale consisting of a series of items to which the subject
responds. The respondent indicates his/her agreement or disagreement with each item on
an intensity scale. For example:
The future looks very bright:

strongly agree agree undecided disagree strongly disagree

5 4 3 2 1
When an individual responds to these statements he/she expresses his/her attitudes on a
scale of 1 to 5 with being in strong agreement of the statement. These scales can be
arranged with many other similar items. When the items all are summed, the total number
is an indication of some general attitude.
(iii)equal- appearing interval scale/ Thurstone scale :- this technique was developed by L.
L. Thurstone. This scaling technique requires items to be selected by a panel of judges.
These items are then evaluated on the basis of relevance to the topic area potential for
ambiguity and the level of attitude they represent .The Thurstone scales consists of a
number of items which a subject responds to by either indicating his/her agreement or
disagreement. The main characteristics of Thurstone scales are that all the items on the
objective test are of equal importance, but actually some items are given higher values
than other items. For example:
My job is like a hobby to me (10.0)
I am satisfied with my job for the time being (7.2)
I am often bored with my job (3.2)
Most of the time, I have to force myself to go to work (1.)

When the data are collected from various respondents, mid value or median is computed
to search a conclusion.
(iii) Guttman scales (cumulative):- The cumulative scale like the other scales consists of a set
of items which are answered unlike the other two scales, the Guttman scales tend to be
cumulative, that is, if a person can answer the first item he/she probably will be able to
answer the second. Or, if a person cannot answer the last item, then he/she probably not
able to answer any of the items. An example of Guttman scales given by F. N. Kerlinger
is as follows:

Four children were given three arithmetic items:

(a) 28/7 = ?
(b) 8x4 = ?
(c) 12+9 = ?

32
 A child who gets (a) correct is very likely to get the other two correct. The child who
misses (a) but gets (b) correctly is likely to get (c) correct. A child who misses (c) is
not likely to get (a) and (b) correct. The situation can be summarized as follows:

(a) (b) (c) Total

First child 1 1 1 3
Second child 0 1 1 2
Third child 0 0 1 1
Fourth child 0 0 0 0

1 = correct, 0 = incorrect

This scale is mostly used in intelligence test of the individuals and more popular in
psychology and education.

Reliability and validity of measurement:-

Data are considered to be valid when they measure what they are supposed to measure. Validity generally
results from careful planning of questionnaire or interview questions. Reliability is a quite different
element. Data are considered to be reliable when they give assurance that they are reasonably close to the
truth. The researcher should keep in mind the possible sources of error. Errors are mainly respondent
related and instrument or questionnaire-related. A brief description about validity and reliability has been
made as follows.

1. Validity:- Validity is concerned with systematic error. A valid measurement reflects only the
characteristics of interest and random error. There are three basic types of validity which are
mentioned as follows:
(a) Content validity: It involves assessing the representativeness or the sampling adequacy of the
items contained in the meaning of the instrument. The most common use content validity is with
multi-items measures. In such case, the researcher assesses the representativeness or sampling
adequacy, of the included items in the light of the purpose of the measuring instrument. The
most commonly used methods of content validation involve the use of logical and personal
judgments or groups of experts in the field.
(b) Construct validity: - It is concerned with knowing more than just that a measuring instrument
works. It is involved with the factors that lie behind the measurement scores obtained; for
example – if a researcher wants to know the working efficiency of the workers in a factory, then
he/she finds out all the independent, dependent, and intervening variables as on the job training,
work satisfaction, bonus, insurance, reward, punishment etc. and tries to correlate them to find
out the truth.
(c) Criterion- related validity:- It is established when the measure differentiates individuals on a
criterion it is expected to predict. This validity involves assessing the extent to which obtained
scores may be used to estimate an individual’s future standing with respect to the criterion
variable. For example, a researcher can predict about the future of a student who has scored high
points or marks during various tests.
2. Reliability:- The researcher must also be concerned with the reliability or his/her measuring
instruments or scale. It means, a measurement device is reliable when it will consistently produce
about the same results when applied to the same samples or to different samples of the same size
drawn from the same population. There mainly two types of reliability such as :
(a) Test – retest reliability:- These estimates are obtained by repeating the measurement using the
same instrument under as nearly equivalent conditions as possible. The results of the two

33
 administrations are then compared and the degree of correspondence is determined. The greater
the difference, the lower the reliability.
(b) Split-half reliability:- It is the simplest type of internal comparison. This approach to measuring
reliability of a measurement instrument is really a modification of the alternative form approach.
It is obtained by calculating the correlation between two halves of an instrument. The usual
approach to split-half reliability involves dividing the total number of items into two groups (odd
numbered and even numbered items) and computing a measure of similarity (a correlation
coefficient). The greater the difference, the lower the reliability.

Chapter V

SAMPLING

Concept of sampling design:

Sampling is an essential part of any research design. Almost all research studies involve sampling. The research
studies assume that the people selected for studies are representative of a large group about whom generalizations
are to be made. The researchers normally cannot survey everyone in the population; but through sampling
techniques, they can be confident that only a small part of the total population can fairly represent the total
population. Sampling, then, is a technique that saves time and trouble of questioning 100 percent of the population.

A sample is a collection of items or elements from a population or universe. Hence, a sample is only a portion or
sub-set of the universe or population. It comprises some observations selected from the population. For example- if
50 households are drawn from a population of 500 households of a community, these 50 households are considered
as samples.

Population or universe refers to the entire group of people, events, or things of interest that the researcher wishes to
investigate. For example- if a researcher is interested in investigating the smoking habit of employees in a chemical
factory, then all employees in that factory will form the population.

In designing a sample, the researcher must consider the following three concepts:

(1) The sampling frame: - It s the list of items in the universe from which the sampling is to be drawn. Thus, it
may be all the students of a campus, all names in the telephone directory, or all households in a community.
(2) Selection of sampling items: - After determining the sampling frame, the researcher must decide how
samples will be selected. Basically, the choice involves selection of probability or non-probability
techniques.
(3) Sample size: - Sample size should be larger. It means, greater the sample size, greater the reliability.
Samples should be taken at least 20% from the universe.
Sampling process:

The sampling process has seven steps, which are presented as follows:

34
 Step – 1 Define the population

Step – 2 Specify the sampling frame

Step – 3 Specify sampling unit

Step – 4 Selection of sampling method

Step – 5 Determine the sample size

Step – 6 Specify the sampling plan

Step – 7 Select the sample

A short description about each step of sampling process is made as follows:

(1) Define the population: - Population must be defined in terms of elements, sampling units, extent and time.
Defining a population incorrectly may render the results of the study meaningless or even misleading. Thus a
research project is required to define the population before the study.
(2) Specify the sampling frame: - A sampling frame is a means for accounting for all elements in the
population. A sampling frame may be telephone directory, an employee roster, a list of all residents in a locality.
Thus, a perfect sampling frame is one in which every element of the population is presented.
(3) Specify sampling unit: - The sampling unit is the basic unit containing the elements of the population to
be sampled. It may be the element itself or a unit in which the element is contained. The sampling unit
selected is often dependent upon the sampling frame. The selection of sampling units is also partially
dependent upon the overall design of the project.
(4) Selection of sampling method: - The sampling method is the way the sample units are selected. There are
several methods or techniques of selecting samples, such as: probability and non-probability sampling
methods.
(5) Determination of the sample size: - The number of elements of the population to be sampled is chosen.
There are qualitative and quantitative factors, which must be addressed when choosing a sample size that
will satisfy the research objective.
(6) Specify sampling plan: - The sampling plan involves the specification of how each of the decisions made
thus far is to be implemented. The operational procedures for selection of the sampling units are thus
selected.
(7) Select the sample: - The final step in the sampling process is the actual selection of the sample elements.
This requires a substantial amount of office and fieldwork, particularly if personal interviews are involved.

Types of sampling:

Samples may be classified into two broad categories, which are: probability samples and non-probability samples. In
probability sampling, each item or element in the universe has equal chance of being selected. But in non-probability
sampling, all items in the universe do not have equal chance of being selected. Detail description of each type has
been made a follows:

1. Probability sampling: - It is also known as random sampling or chance sampling. Under this sampling design,
every item of the universe has an equal chance of inclusion in the sample. It is a method in which individual units
are picked up from the whole group not deliberately but by some mechanical process. There are four types of
probability sampling such as :

35
 a) Simple random sampling: - In a simple random sampling scheme, all items of the population has equal
probability of being selected in the sample. This method is used only in those studies where the entire
population can be listed. For this, first of all , a researcher has to list all the population in a sampling frame and
after that he/she can take desired samples using lottery method, random number or table developed by Tippet,
grid method or blind fold selection method.

Merits:

 It is a time saving and economical method.

 It can cover larger geographical area or large population.
 It is applicable in all types of research design.
 It is very easy method, flexible and even helpful for experimental studies.

Demerits:

 It needs highly qualified and experienced manpower.

 Difficulty in selecting representative sample.
 Chances of biasness.
 Impossibility in accuracy and actual validity due to the heterogeneous nature of society.
b) Stratified random sample: - This sampling method is used when a researcher has to select samples from a
heterogeneous population. In this sampling, the population is divided into various sub-groups or strata and a
simple random sample is taken from each sub-group. The units thus picked up from the sub groups together
constitute a stratified sample. Because samples are selected from each stratum, we can be sure that each
segment of the population is presented in our study. For example- we have to select 300 students from a
campus for our study. We have to stratify the student population of the campus in different strata by their sex,
age, religion, family income etc. Here, we have to select samples using random sampling methods.

There are two types stratified random sample, such as: proportionate stratified sampling and disproportionate
stratified sampling method.

Merits:

The researcher can control the total samples.

It takes short time and minimum expenditure.
Comparative study between the strata is possible.
It is applicable in heterogeneous population.
Replacement and manipulation of the sample is possible.

Demerits:

 Chances of biasness.
 It needs highly experienced and qualified manpower.
 Difficulty in selection of representative sample.
 Difficulty in stratification into various strata.
(c) Cluster sampling: - In some cases, population may be too large to allow cost-effective random sampling or even
systematic sampling. Cluster sampling is best used when these sampling are not possible. We might be interested
in surveying the position of workers in a district or region. To make sampling more manageable, we could identify
naturally occurring groups of participants or clusters and randomly select certain clusters. Once the clusters have
been selected we would then survey all participants within the cluster.

36
 For example – we want to study the problem of labor-strike in the industrial sector in Nepal. The first step would be
to obtain a list of all factories in Nepal. This will constitute our sampling frame but the number of factories and
employees is too large. We might then select 2 – 3 clusters (factories) from east to west which constitute the
secondary sampling frame. And finally, we would select individual factories and employees from each of these
regions.

Merits:

 The samples selected by this method are considered the representative of a universe.
 The study of large population is possible through this method.
 It saves time and expenditure.

Demerits:

 It is difficult to determine the appropriate sample due to heterogeneity.

 It needs highly qualified and experienced manpower.
 False sample selection may lead to wrong results.
(d) Systematic sampling: - This type of sampling is for all practical purposes, an approximation of simple random
sampling. It requires that the population can be uniquely identified by its order, for example – the residents of a
community may be listed and their names arranged alphabetically. Each of these names may be given a number
and such an index is known as the frame of population. Suppose, this frame consists of 1000 members each with
a unique number, i. e. from 1 to 1000. Let us say, we want to select a sample of 100. We may start by selecting
any number ‘between’ 1 to 10 (both included). Suppose, we make a random selection by entering the list and get
3. When we proceed to select numbers, starting from 3with a regular interval of 10. The selected sample would
be thus consists of elements bearing numbers 3, 13, 23, 33, 43, 53, 63……….. 983, 993. These elements together
would constitute a systematic sample.

Merits:

 It is easy and less time consuming method.

 It can study a large population.
 Representative samples can be drawn if the items in a population are thoroughly mixed.
 It saves money.

Demerits:

 It doesn’t afford all possible combination of cases.

 The result drawn from this method is quite unacceptable if the items are not thoroughly mixed.
 Chances of biasness.
 Difficult to select representative sample.
2. Non-probability sampling: -

This is the method of selecting samples in which the choice of selection of sampling units depends entirely on the
decision or judgment of the researcher. It means, the distinctive characteristic of non-probability sampling in
contradistinction to the probability sampling is that sampling procedure adopted in this design does not afford any
basis for estimating the probability that each element in the population has an equal chance of being included in the
sample. In such a sampling, there is no assurance that every element has some equal chance of being included in the
sample. It is clear that, in the non-probability samples, there is no way of estimating how much confidence may be
placed in the sample returns as to their being within a specified margin of error.

37
This method is mainly used for opinion surveys, but cannot be recommended for general use as it is a subject to the
drawbacks of prejudice and bias of the investigators. However, if the researcher is experienced and qualified, it is
possible that non-probability samples may yield useful results.

Major types of non-probability sampling are as follows:

a) Quota samples: -One of the most commonly used methods of sampling in marketing research and opinion poll
is the method of quota sampling. In quota sampling, the interviewer is instructed to collect information from an
assigned number of quota, of individuals in each of several groups. The groups being specified as to age, sex,
income or other characteristics like the strata in stratified sampling. Quota sampling usually proceeds in three
stages:
(i) First: - Classification of population in terms of different characteristics (strata).
(ii) Second: - Determination of number of items / individuals to be interviewed.
(iii) Third: - Assignment of quota for the observer / interviewer. The responsibility of selection of items is
given to the interviewer.

Quota sampling is cheaper method and occasionally provides satisfactory results if the interviewer is well-trained
and unbiased.

b) Accidental sample: - In accidental sampling, the researcher simply reaches out and pick up the cases that fall to
hand, continuing the process till such time as the samples acquire a desired size. For example – a researcher
wants to know how the people feel about an issue may choose to interview cases accidentally available from
different walks of life, i. e. teachers, workers, taxi-drivers, retail shopkeepers, housewives and others who are
presumed to reflect public opinion. However, there is maximum chance of biasness in this sampling design, but
it doesn’t mean that accidental samples do not have any place in scientific research. This type of sampling,
besides being economical and less time consuming, can also a helpful method for hypothesis formulation where
too much accuracy is needed. So, the procedure of accidental sampling is quite useful.
c) Purposive or judgmental sampling: - These types of samples are selected from the population through
researcher’s choice or judgment or on some other subjective basis. The selection of sample is deliberate and
purposive; it is not random. The key assumption underlying this type of sampling is that, with sound judgment
or expertise and an appropriate strategy one can carefully choose the elements to be included in the sample. The
intent is to select elements that are believed to be typical or representative of the population in such a way that
errors of judgment in the selection will cancel each other out. Thus, sample representativeness is highly
depended upon the good judgment of the researcher. Probably the most valid usage of judgmental sampling is to
obtain expert opinion. Purposive or judgmental sampling can be very misleading if they are not interpreted as
accurate reflection of universe characteristics. Thus, result of such sample study cannot be generalized.
d) Convenience sampling: - Convenience sampling refers to samples selected not by judgment or probability
techniques rather samples are selected conveniently up to the desired numbers. There is no attempt made to
have a representative sample. Selection of sampling units is totally based on the facility of the researcher. When
both time and money are seriously limited, convenience sampling is widely used. For example – if we have to
conduct “man on the street” interview, we probably use convenience sampling. We may stand up in a corner of
a street and interview the desired number of passer-by.

Thus, the most easily accessible items of the population are chosen as subject. Although this sampling method is not
very scientific, it is perfectly valid in the pre-test phase of a study where there is a need to get only an approximation
of the actual value. This method is quick, easy and less expensive.

38
Sampling Vs non-sampling errors:

(a) Sampling errors: - In sample surveys, since only a small portion of the population is studied, its results are
bound to differ from the census results and thus have a certain amounts of errors. Thus, the error arises due to
estimating population parameters only by selecting few units (samples) is called sampling error. This error is
inherent and unavoidable in any and every sampling scheme. A sample with the smallest sampling error is
considered to be a good representative of the population and this error can be reduced by increasing the size of
the sample.
The sample errors committed due to the following condition:

 Selection error: - Errors arouse due to the improper selection technique, improper selection method,
inadequacy of sample size, and improper sample design.
 Estimation error: - Biased parameter estimate because of the complex elements in the samples.
 Sampling bias error: - Tendency to favor the selection of particular unit intentionally or unintentionally
having particular characteristics in the population.

Minimizing sampling errors:

(1) Increase the sample size: - The more sample size is, the less sampling errors.
(2) Cross checking: - Errors can be minimized through the use of different data collection method and their
cross checking.
(3) Proper and unbiased probability sampling method should be selected.
(4) Revise the design of the questionnaire (questions must not be misleading, unclear, and difficult to
understand).
(5) Strong sampling plan (selection of proper sampling techniques, accuracy of sample size, and proper
coverage of sampling frame).
A. Non sampling errors: -Non sampling error can be defined as errors arising during the course of research
rather than resulting from the sampling procedure. Non sampling errors can occur because of problems in
coverage, response, non-response, data processing, estimation and analysis. Unlike sampling errors, there
is no simple and direct method of estimating the size of non sampling errors. Unlike sampling error,
increasing the sample size will not have any effect on reducing non sampling errors.
Generally, non sampling errors arise from the following factors:

(i) Over coverage: - Inclusion of data from outside of the population, duplication or wrong inclusion
of units in population cause over coverage.
(ii) Under coverage: - Sampling frame does not include elements in the population. Omission of
requisite units in population cause under coverage.
(iii) Measurement error: - The respondents misunderstand the question due to poor questionnaire,
untrained enumerators, or due to low awareness levels of respondents.
(iv) Processing error: - Mistakes in data coding, processing and analyzing or interpretation cause
errors.
(v) Response error: - No response, bias response, inability to answer, cheating, unwillingness,
misinterpretation of the question, response recorded incorrectly, inadequacy of response collected
as per required to valid and reliable, incompleteness of response and poor questionnaire add
response error.

(vi) Researcher’s error: - No clear definition, selection of wrong method, poor questionnaire and its
improper administration and intentional errors lead to non sampling error.

39
 (vii) Field worker/ enumerator error: - Biases, misinterpretation of question, poor interview, weak
inclusion and rapport and intentional errors.

Minimizing non sampling errors:

(i) Employing qualified and trained manpower for the planning and execution of survey.
(ii) Using more sophisticated statistical techniques and equipments for the processing and analysis of
data.
(iii) Providing adequate supervisory checks on the field work.
(iv) Pre-testing or conducting a pilot survey.
(v) Thorough editing and verifying of the results.
(vi) Effecting checking of all the steps in the processing and analysis of data.
(vii) More effective follow up of non response cases.
(viii) Providing training to the investigators for efficient conduct of the inquiry.

Chapter-6

DATA COLLECTION

DATA:

The facts which can be used as statistical procedures and can be measured are called the data. So, data
are facts or figures such as alphabets, numerals, symbols, graphs, images, videos particularly as
measurements or observations of a set of variables from which conclusions can be drawn. When data
have been recorded, classified, organized and interpreted within a framework, so that meaning
emerges, they become information. In this way, data are the basic units of every research activity and
hence, research mission cannot be completed without data. Data may be quantitative or qualitative or
primary or secondary, all types of data are equally important in the research activities. Thus, without
data, methodology cannot be utilized to bring us to the conclusion, which the hypothesis suggests.

Classification of primary and secondary data:

1. Primary data: - Data collected by the researcher or through agent for the first time from related
field and possessing original character are known as primary data. It means, primary data are
original data gathered by the researcher expressly to solve the problem under consideration.
Such data have not been previously collected or assimilated for any other projects. There are
several ways of gathering primary data. These data sources can be classified into three
categories : questionnaires, interview and observation. For each of these methods, there is a
particular set of tasks to be performed. Different procedures should be followed depending on
the method of primary data collection used.
2. Secondary data:- Data that have already been collected by somebody for some other purpose
are termed as secondary data. There are two main types of secondary data : documents and
records, and surveys. Any secondary data we use in our research was collected by others for
their own purpose. This purpose may not match with that of our study. Also, the secondary data

40
 are likely to be less current than any data we collect ourselves. Therefore, once we locate
secondary sources, we have to ensure their overall suitability for our research questions and
objectives.
Sources and use of secondary data:

Secondary data are often in the form of raw data and published materials. However, the unpublished
data such as the records, reports or statistics gathered or compiled by others prior to our study are also
secondary data. Secondary data can also be purchased in many cases from commercial research
agencies. Secondary data are actually the results and data collected by previous investigators. It
provides the researcher with a considerable amount of useful information. Secondary studies take
existing collected information and examine relation among variables. In other cases, a researcher will
collect empirical on one variable and then sees if it can be related to variables from secondary data. The
most distinguishing aspect of secondary data collection is that an instrument does not need to be
developed.

The main data collection activity of the investigator is locating appropriate data. The students may not
find all the information in published journals and reports, although these are excellent starting sources.
Frequently it becomes necessary to visit agencies and bureaus, which compile and collect data. It then is
necessary to inquire if the desired data exists, and if it is in office files. Also, when the data is obtained, it
is necessary to evaluate the data for its accuracy.

The sources of secondary data are presented as follows:

(i) Documents and Records

(a) Written documents and records
- Organizational records, notice and publications
- Books
- Journals
- Newspapers
- Research reports
- Committee reports
- Web sites and Internet
(b) Non- written records
- CD- ROMS
- Films
- Taped interviews
- TV and radio recordings
- Picture and drawings
(ii) Surveys
(a) Censuses
- Population
- Industrial
- Employment
- Land holdings
- Agricultural
(b) Regular and occasional surveys

41
 - Price index
- Family income and spending
- Labor market
- Import and export
- Organizational surveys
- International indexes
- Attitude surveys
- Occupational surveys, etc.
Secondary data sources in Nepal:

- National planning commission

- Different ministries and departments of government
- Central Bureau of Statistics
- Nepal Rastra Bank
- National Productivity and Economic Development Center
- Center for Economic Development and Administration
- Trade Promotion Centre
- TU, NGOs, INGOs
- Federation of Nepalese Chambers and Commerce and Industries, Etc.
Sources of primary data

Questionnaire (content, design and administration)

The main tool that is used in survey research is questionnaire. A questionnaire is a formal list of
questions designed to gather responses from respondents on a given topic. Thus, a questionnaire is an
efficient data collecting mechanism when the researcher knows exactly what is required and how to
measure the variables of interest.

A questionnaire involves several steps including writing question items, organizing the question items on
a questionnaire, administering the questionnaire and so on. We should remember that a collection of
questions does not make a questionnaire. The questions must be organized into a sequential order and
visually pleasing format. This process involves paying attention to the design of the questionnaire. An
organized questionnaire is much easier and more enjoyable for the respondent to complete. This may
also increase the response and completion rates.

Design:

A questionnaire can be designed to secure different types of primary data from the respondents.
However, we should pay particular attention to what information we would like to seek from the
respondents. The issue of questionnaire design is also essential for quality data collection. Good
research is about asking the right people the right questions- not much more and not much less. The
questionnaire design that draws out accurate information, that can be completed easily by the
researcher, that follows well, and that leaves the respondents feel satisfied for their worthwhile
participation in that research , can be described as an effective design. Thus, the keys to successful
questionnaire design are : order, wording, layout, length and appearance which are described as
follows:

42
(1) Information desired: - We should make a plan of our information requirements. Collecting
unnecessary information may consume more of our time and resources. So, only the desired
information should be collected through a questionnaire.
(2) Types and formats of questions : - Types of questions refers to whether the questions will be
open-ended or closed. Open-ended questions allow respondents to answer them in any way
they choose. A closed question, in contrast, would restrict the respondents within the
alternatives given. The questionnaire should be designed in such a way that it is easy to read
and the responses are easy to fill in.
(3) Length: - Simple and short questions are preferable to long ones. The longer the questionnaire,
the more the costs to administer and to interpret the data obtained. Long questions consume
more time of the respondents. This may discourage the respondents to complete the
questionnaire.
(4) Wording: - The words used in the questions should not be ambiguous. Ambiguous questions are
those that do not convey a clear meaning to the respondents. To avoid ambiguity, we should
use simple words that are easily understood by the people of any educational and cultural
background.
(5) Order: - This is another important aspect of questionnaire design, the related questions should
be logically ordered. Question order is specially important when multiple choice questions are to
be used. Generally, questions move from general to particular. The usual practice is to be gained
with general questions and then lead to specific ones.
(6) Physical appearance: - Attention should be paid in order to give a good physical appearance to
the questionnaire so as to get good response from the respondents. The matters that require
special attention including quality and size of paper, quality of typing or printing, attractive
presentation of question items , including margin and spacing.
Administration:

The researcher’s performance in questionnaire administration can be measured usually with respect
to four aspects:

(1) Contact rate: - Making contact with respondents could be a problem in some cases. The
proportion of addresses or eligible names with which the researcher makes contact measures
this rate.
(2) Response rate: - Non- response could also be a problem in some research activities. The
proportion of contact that results in interview measures the response rate.
(3) Completeness rate: - Questionnaire returned incomplete are useless. The proportion of
information obtained to that desired measures the completeness rate.
(4) Accuracy rate: - The accuracy rate is defined as the ratio of measured to true value.
Some guidelines for questionnaire administration:

- Include in the questionnaire a small token of appreciation, such as a pen or pencil

that the respondents can keep.
- Pre- contact the respondents about the questionnaire that will be mailed to them.
Pre- contact is most effective when done by telephone.
- Send follow- up letters or remainders to respondents one or two weeks after
sending out the questionnaires.
- Provide the respondents with self- addresses and stamped return envelopes.
- Deadline of the questionnaire filling and sending should be remembered to the
respondents.

43
 - The efficiency of the postal and currier services should also be checked.
- Try to make questions as interesting as possible.
Pre- testing of Questionnaire:

- Select a sample of individuals who are representative of the population toward

which the questionnaire is eventually intended.
- Provide space on the trial questionnaire for the respondents to make reactions and
suggested changes.
- Check the percent of responses as an estimate of what will occur in the final run;
then examine the troubles signs such items left blank ,misinterpretation and
ambiguities .check the comments for similar indications.
- Analyze the results to assess to effectiveness of trial questionnaire to yield the
information desired.
- Make appropriate additions and modifications to the questionnaire.
- Determine overall reactions of subjects to the questionnaire (what did they like,
dislike or want modified?)

A model of questionnaire:

Impact of agricultural road in local economy: A case study of Rajarani Village, Dhankuta

Questionnaire

Q.N. Date/time of interview S.N. Code No.

1. Personal information

1.1 Name of the respondent

Ward No- Location

Age Sex

1.2. Education

(a) Illiterate

(b) Literate

(c) Completed class/ level

1.3. Family head

(a) Respondent himself/ herself

44
(b) Family size sex No.

1.4. Household composition

S.N. Name Relation of respondent Education Main occupation Allied

occupation

2.Economic back ground

2.1 What is your land size holding and production?

Khet (Ropani) Production (Kg.) Pakho(Ropani) Production(Kg.)

2.2. What is your land tenure system?

(a) Owner cultivates (b) Tenant cultivates (c) Rented (d) Other specify…………

2.3 Occupation before agricultural road construction (2003)

(a) Agriculture (b) Wage earner (c) Retail business (d) Livestock (e) Poultry (f) bee
keeping (g) Other………

2.4 Current major occupation

(a) Agriculture (b) Wage earner (c) Retail business (d) Livestock (e) Poultry (f) Beekeeping (g)
Other…………

2.5 Family income ( before the road construction) In Rs………… (monthly)

2.6 Current family income (monthly) Rs…………..

Research Interview: Personal and Telephone

This technique of collecting primary data is widely used in research. Interviewing has became a very
popular tool for conducting research in the fields that do not demand experimental works. It is well
established, practicable and reliable method of data collection. Interviews can be held in the
respondent’s home or place of employment or any other suitable places. The researcher may ask

45
questions on the issues of his/her research interest and record the answers of the respondents in a
sheet of paper. The information thus collected would provide valuable insights into the phenomena
under investigation.

According to F. N. Kerlinger, “ The interview is a face to face interpersonal role situation in which one
person, the interviewer, asks a person being interviewed, the respondent, questions designed to obtain
answers pertinent to the purpose of the research problem.”

The interview is a method allowing the researcher to ask questions which will enable him/her to answer
research questions. There are different types of interviews. The interviewer may ask questions and then
suggest a list of possible answers; this is a structured interview. On the other hand, if a data collector did
not know what exact information he/she could obtain, then he/she could ask questions letting the
interviewee answer them in his/her own style. The later technique is called unstructured or open
interview.

Beside face to face interviews, telephone interview today is a well established technique of data
collection. With the telephone becoming more and more widespread, there is also a growth in the
number of research being conducted through telephone. In a telephone interviewing, the interviewer
contacts respondents by telephone. The questions asked are more or less of structured nature. The
interviewer uses a structured interview schedule to be administered. This type of interviewing is best
suited when many respondents are to be researched over a geographical area and the time available for
interviews is very short. Similarly, some questions can be asked more easily over the telephone than in
written form. However, because questions are asked verbally, the interviewer must be careful about the
use of words.

Principles of interviewing:

Interview is not only a method but also a skill and art. So, while interviewing, some values and
limitations should also be considered. Thus, some basic principles of interviewing should be followed by
a researcher, which are mentioned as follows:

(i) A researcher must be sincere and honest to his/her purpose of research.

(ii) He/she should build trust with the respondents.
(iii) He/she should be cooperative in his/her behavior.
(iv) Questions should be flexible and relevance to the research questions.
(v) Research should be bias less in terms of caste, religion, sex, political belief and economic
condition.
(vi) A researcher should never be as a teacher or director, and she/he should provide an
opportunity to express answers freely to the respondents.
(vii) A researcher should try to motivate the respondents for free expression.
(viii) A researcher should greet or welcome to the respondents and should always use respective
and formal words.
(ix) A researcher should not make any debate and unnecessary logic with the respondents.
(x) Never be proudly.

46
 (xi) Don’t loss control over the interview.
(xii) A researcher should be a good listener.
(xiii) A researcher should play a role of facilitator rather than a scientist.
(xiv) After completion of interview, a researcher should greet and acknowledge to the
respondents again.

Qualitative data collection: Focused group/ Depth interview:

Group interviews involve two or more interviewees. A focus group generally involves 6-10 persons. They
are brought together at one place to discuss the topic of interest. This type of interview is more suitable
for gathering information about certain specific issues. Particularly, the inner feelings and emotional
attitudes of the interviewees with respect to a given problem or situation are studied. Therefore, the
focus group interviews focus attention on the background of emotional and intellectual atmosphere of
the problem.

When the focus group is organized, the interviewer (moderator) provides a brief general comment on
the purpose of the meeting and suggests a specific topic to open the discussion. From this discussion,
the moderator may move the group to talk about how they feel about the subject or issue of interest
and move them to a discussion of their attitudes and opinions toward the issue. The moderator doesn’t
interfere too often during the discussion. The moderator intervenes when a topic has been finished or to
bring the discussion back to the main issue when it goes outside the theme of discussion.

Focus group interviews are usually taped so that the moderator can concentrate on keeping the
discussion on track without fear of losing any information. When tape-recorded, the moderator can
analyze the results later at his/her facility. Focus groups have become popular in marketing research
because they give a direct ‘feel’ of the individual consumers.

Focus groups are successful only when skilled moderators conduct them. It is generally believed that a
good moderator should be well trained in behavioral science, should have some experience with the
subject under study, and must have a proper skill for grasping the important points developed in the
discussion. But focus groups have problems that even the best moderators cannot easily eliminate.
Dominant personalities may take over groups and lead the discussion in their own way.

Participative method:

Participation of local people in the research activity for the collection of qualitative data and for solution
of rural problem is called the participative method. Although there are various methods of participative
research, but the PRA (participatory Rural Appraisal} and RRA (Rapid Rural Appraisal) methods have
been commonly and widely used by the social scientists to address the rural problems and to collect

47
qualitative data from the universe. This method is very popular in sociology, anthropology and rural
development and thus, this method is mostly used by the non-governmental organizations. A brief
description about PRA and RRA method has been presented as follows:

(1) Rapid Rural Appraisal (RRA) : - Rapid Rural Appraisal consists of a series of techniques for quick
and dirty “ research” that are claimed to generate results of less reliability and validity,
but greater evidential value than classic quantitative survey techniques. The method does not
need to be exclusively rural nor rapid, but it is economical of the researcher’s expenditure and
time.
This method was developed during the decade of 1990s through which wider information can
be gathered in a short period and less expenditure. Generally, information are collected by the
educated, experienced and forward people of the community. His method is conducted before
project formulation and after termination of the project. The researcher plays a dominant role in
this method and only a few selected community people are considered as the sources of
information. It is also called “direct method of data collection “ or “ client request study” . This
method is widely used for SWOT analysis and the impact study of development study.

(2) Participatory Rural Appraisal (PRA) : - PRA is a modern technique of participatory research
intended toward mutual gain of data collection as well as empowerment of targeted people,
different from conventional method with no rigid formalism. It ensures the people’s active
participation from the very beginning to the end of entire processes. This method is guided by
the principle of “Putting People First” in which all levels of people are encouraged to participate
in the discussion and the researcher plays a role of facilitator. This method believes that the
local people are the experts of their community and their skills and knowledge would be the key
for the solution of problems. In this method, decision process is democratic and no decision is
made by the researcher without participation of people. The PRA method has three main
objectives, such as : problem solution, active participation and empowerment. This is latest
approach developed by a famous sociologist Robert Chamber.
Principles of PRA:

- Sit down, listen, watch and learn (for researcher)

- Substantial use of indigenous knowledge (local people are exports)
- Make the study more valid and reliable ( involve maximum people, their experience
may make the study more reliable)
- Apply flexibility ( no rigid rule for participation and expression of local ideas)
- Embracing the errors ( research should be positive about mistakes , they should
recognized share and learn from the mistake)
- Trust on rural people that they can know it and do it.
Observation : Participant and non- participant:

Literally, observation is watching, listening, and reading something carefully in the natural condition. In
Concise Oxford dictionary, observation has been defined as “accurate watching, noting of phenomena as
they occur in nature with regard to cause and effect relationship.” Similarly, P.V. Young defines the term
as “Observation may be defined as systematic viewing, coupled with consideration of seen phenomena”.

48
Thus, observation is nothing else but seeing the things either from distant or going near to the object of
study. Observation implies the use of eyes rather than of the ears and the voice. Ability of observer
determines the success of observation. It is a most reliable and perfect method of data collection in the
natural settings. It is very popular in HRM research, psychology, education, sociology and anthropology.

Observation involves three processes such as sensation, attention and perception. Sensation is gained
through the sense organs. Attention which is largely a matter of will power and perception comprises
the interpretation of sensory reports. Through this process, observation serves the following purposes:

- Studying collective behavior and complex social institutions

- Following up of individual units composing the situations
- Understanding the whole and parts in their interrelations
- Getting out the details of the situations
Types of observations:

(1) Participant observation: - When the observer participates with the activities of the group under
study, it is called participant observation. For example – if the researcher wants to study the
behavior of hostel students, it will be easier to study the students in their natural circumstances if
the researcher enrolls personally as a member of the hostel. Thus, the participant observer becomes
as a part of the group and known as participant observer. The degree and the period of participation
may vary with the purpose of the study and the practical demand of the situation; i. e. the
researcher need not necessarily carryout all the activities as carried out by other group members
but the researcher’s presence is necessary for complete observation. The observer mixes with social
activities of the group, their normal workings, functions and festivals and keeps essential records or
data for the desired study.
This method has some merits and demerits. This method is able to acquire wider information, it is
helpful for exchanging of ideas and it has the possibility to draw the natural and real behavior of the
group, Similarly, it has some drawbacks like it takes longer time, greater resources are required and
there is chance of biasness.

(2) Non participant observation: - When the researcher does not actually participates in the
activities of the group to be studied, but simply present in the group it is called non- participant
observation. In this method, the observer does not make effort to his/ her influence or to create
a relationship between him/her and group. It is extremely difficult in practice because it is not
possible for an observer to be present but not participate in activities.
This method has so many advantages that the researcher is able to acquire information without
influence because he/she keeps him/herself away from the activities of the group. The observer can
maintain purely impartial status to get the cooperation from every member of the group. Similarly
the observer remains unattached and impartial without having any prejudices.

But there are also some disadvantages of this method that adequate and complete observation is
not possible through this method. There is chance of unnatural attitude of the subject matter of
observation and the findings are generally based through personal prediction and preconceptions.

Designing and conducting an observational study:

49
 While designing and conducting an observational study, the researcher should proceed the following
steps:

(1) Determination of the method of study: - The method either participant or non participant
should be determined according to the nature of research topic.
(2) Determination of nature and limits of observation: - This helps to guide the researcher as to
what should be observed and what may be left out.
(3) Determination of time, place and subject of study: - A decision regarding the time, place and
subject of the research has to be taken. It may be studied under laboratory conditions or in the
open.
(4) Determination of investigators: - for actual observations, the research usually requires team of
trained experts. In certain cases, help can be taken from the experts of other sciences.
(5) Determination of mechanical aids: - some equipment like photo camera, movie camera, tape –
recorder and other devices are required.
(6) Data collection: - collect the data which are fit in to the research hypothesis.
(7) Classification and tabulation of data.
(8) Generalization.
Use of Internet for data collection:

Nowadays, the earth has been changed into a small global village due to the information revolution and
rapid development in communication technology. This development has brought changes even in the
research field. The World Wide Web (WWW) has become a large store of information through which all
types of data and information can be collected and such uses have been increasing day by day. Both
primary and secondary data can be collected through the use of internet. Such collected data can also
be interpreted and analyzed through different computer software like excel and SPSS (Statistical
Package for Social Sciences).

Internet data collection is a means of quick survey data collection by utilizing the internet. Respondents
fill in their returns using browser based internet forms. A system administrator subsequently retrieves
the completed forms and routes them for further processing. If there are other modes of data capture,
the system administrator will consolidate the returns submitted through internet with those obtained by
the other modes.

There are four methods of internet data collection, such as:

(1) Computer assisted telephone interviewing

(2) Computer assisted personal interviewing
(3) Computer assisted survey
(4) Computerized self-administered questionnaire
Advantages:

(i) It reduces manpower effort on data entry and data editing.

(ii) This method is time saving if the submitted forms are clear and complete.
(iii) This will help to make possible quicker release of results.
(iv) It makes easy to compile data.
(v) Dissemination of statistical information can be done within a short period of time.
Disadvantages:

50
 (i) It is not applicable to all types of research studies.
(ii) It cannot cover the remote areas where the access of internet is not available.
(iii) Illiterate and poor people cannot participate in the surveys.
(iv) Universal conclusion cannot be drawn through this method.

Factors affecting choice of data collection method:

Without facts or data one can not specify the characteristics about which the research is to be
conducted. Collection of secondary data doesn’t seek any methodology or design but the primary data
requires pre-assigned, widely acceptable and suitable design. The choice of proper methodology
depends upon various factors like level of research, nature and available resources. So, some factors
affecting the choice of data collection methods are summarized as follows:

(i) Availability of resources and means.

(ii) Social, political, cultural and economic condition of the universe or population.
(iii) Nature and complexity of the research topic.
(iv) The level of sampling and its size.
(v) Limitation of time.
(vi) Nature of research design.
(vii) Skill, experience and ability of the available manpower.
(viii) Availability of physical facilities.
(ix) Recording method of information.
(x) Ability and confidence of the researcher.
(xi) Cooperation of the respondents.
(xii) Selection of sampling design, etc.

Concept of field work Research

Field research or fieldwork is the collection of information outside a laboratory, library or workplace
setting. The approaches and methods used in field research vary across disciplines. For example,
biologists who conduct field research may simply observe animals interacting with their environments,
whereas social scientists conducting field research may interview or observe people in their natural
environments to learn their languages, folklore, and social structures.

Field research involves a range of well-defined, although variable, methods: informal interviews, direct
observation, participation in the life of the group, collective discussions, analyses of personal documents
produced within the group, self-analysis, results from activities undertaken off- or on-line, and life-
histories. Although the method generally is characterized as qualitative research, it may (and often does)
include quantitative dimensions.

History
Field research has a long history. Cultural anthropologists have long used field research to study other
cultures. Although the cultures do not have to be different, this has often been the case in the past with the
study of so-called primitive cultures, and even in sociology the cultural differences have been ones of

51
class. The work is done... in "'Fields' that is, circumscribed areas of study which have been the subject of
social research".[1] Fields could be education, industrial settings, or Amazonian rain forests. Field research
may be conducted by zoologists such as Jane Goodall. Radcliff-Brown [1910] and Malinowski [1922]
were early cultural anthropologists who set the models for future work.[2]

Business use of Field research is an applied form of anthropology and is as likely to be advised by
sociologists or statisticians in the case of surveys.

Consumer marketing field research is the primary marketing technique used by businesses to research
their target market.

Conducting field research

The quality of results obtained from field research depends on the data gathered in the field. The data in
turn, depend upon the field worker, his or her level of involvement, and ability to see and visualize things
that other individuals visiting the area of study may fail to notice. The more open researchers are to new
ideas, concepts, and things which they may not have seen in their own culture, the better will be the
absorption of those ideas. Better grasping of such material means better understanding of the forces of
culture operating in the area and the ways they modify the lives of the people under study. Social
scientists (i.e. anthropologists, social psychologists, etc.) have always been taught to be free from
ethnocentrism (i.e. the belief in the superiority of one's own ethnic group), when conducting any type of
field research.

When humans themselves are the subject of study, protocols must be devised to reduce the risk of
observer bias and the acquisition of too theoretical or idealized explanations of the workings of a culture.
Participant observation, data collection, and survey research are examples of field research methods, in
contrast to what is often called experimental or lab research.

Field notes
Main article: Fieldnotes

When conducting field research, keeping an ethnographic record is essential to the process. Field notes
are a key part of the ethnographic record. The process of field notes begin as the researcher participates in
local scenes and experiences in order to make observations that will later be written up. The field
researcher tries first to take mental notes of certain details in order that they be written down later.

Kinds of field notes

Jot notes

The first writing that is done typically consists of jotted or condensed notes. Thus, key words or phrases
are written down while the researcher is in or very close to the field. Some researchers jot field notes
openly in the presence of those being studied. Adopting this practice early on enables some researchers to
find that they can establish a 'note-taker' role that will be accepted or at least tolerated by those being
studied. However, some researchers find that people develop expectations of what should be recorded and

52
what should not, which can intrude upon the work being done. Other ethnographers try to avoid taking
notes in the middle of scenes and experiences and instead try to place themselves on the margins of
scenes and events. Others strictly avoid writing anything in the presence of those being studied. They feel
that such writing can overtly remind the participants that the researcher has different commitments and
priorities. Such writing can also distract the researcher from what is happening in the immediate scene in
which he or she is participating. Thus, many researchers choose to make jotted notes outside the presence
of those being studied. Some therefore retreat to bathrooms or stairwells in order to record field notes. [3]

Field notes proper

There are three main points regarding field notes proper. First, converting jot notes into field notes should
take place as soon as possible after the events take place. Secondly, field notes should be very detailed.
Thus, included in field notes should be a description of the physical context and the people involved,
including their behavior and nonverbal communication. Field notes should also use words that are as
close as possible to the words used by the participants. Thirdly, field notes should include thoughts,
impressions and explanations on the part of the researcher. In assessing the quality of field notes, the
accuracy of the description and the level of detail are of utmost importance. [4]

Methodological notes

These notes can contain new ideas that the researcher has on how to carry out the research project. Also
included can be which methods are chosen, on what basis they were chosen, how they were carried out
and the outcome of such methods. Methodological notes can be kept with field notes or they can filed
separately. These also serve the researcher when later writing up the methods section of a report or paper.
[4]

Journals and diaries

Journals and diaries are written notes that record the ethnographer's personal reactions, frustrations, and
assessments of life and work in the field. When constructed chronologically these journals provide a
guide to the information in field notes and records.[5] One of the most well known diaries is that of
Bronislaw Malinowski regarding his research among the Trobriand Islanders. [6] During her Pacific
fieldwork Margaret Mead kept a diary and also wrote long letters to people at home which contained self-
reflection that might be included in a diary.

Interviewing
Another method of data collection is interviewing, specifically interviewing in the qualitative paradigm.
Interviewing can be done in different formats, this all depends on individual researcher preferences,
research purpose, and the research question asked.

Analyzing data
In qualitative research, there are many ways of analyzing data gathered in the field. One of the two most
common methods of data analysis are thematic analysis and narrative analysis. As mentioned before, the
type of analysis a researcher decides to use depends on the research question asked, the researcher's field,
and the researcher's personal method of choice.

53
Example of Field work in Management

Mintzberg played a crucial role in the popularization of field research in management. The tremendous
amount of work that Mintzberg put into the findings earned him the title of leader of a new school of
management, the descriptive school, as opposed to the prescriptive and normative schools that preceded
his work. The schools of thought derive from Taylor, Henri Fayol, Lyndall Urwick, Herbert A. Simon,
and others endeavored to prescribe and expound norms to show what managers must or should do. With
the arrival of Mintzberg, the question was no longer what must or should be done, but what a manager
actually does during the day. More recently, in his 2004 book Managers Not MBAs, Mintzberg examined
what he believes to be wrong with management education today.

Aktouf (2006, p. 198) summed-up Mintzberg observations about what takes place in the field:‘’First, the
manager’s job is not ordered, continuous, and sequential, nor is it uniform or homogeneous. On the
contrary, it is fragmented, irregular, choppy, extremely changeable and variable. This work is also marked
by brevity: no sooner has a manager finished one activity than he or she is called up to jump to another,
and this pattern continues nonstop. Second, the manager’s daily work is a not a series of self-initiated,
willful actions transformed into decisions, after examining the circumstances. Rather, it is an unbroken
series of reactions to all sorts of request that come from all around the manager, from both the internal
and external environments. Third, the manager deals with the same issues several times, for short periods
of time; he or she is far from the traditional image of the individual who deals with one problem at a time,
in a calm and orderly fashion. Fourth, the manager acts as a focal point, an interface, or an intersection
between several series of actors in the organization: external and internal environments, collaborators,
partners, superiors, subordinates, colleagues, and so forth. He or she must constantly ensure, achieve, or
facilitate interactions between all these categories of actors to allow the firm to function smoothly.’’

Chapter- viii

Topic selection and Research proposal

The process of formulating and clarifying research topic is an important part of the research
activity. Selection of an appropriate research topic is not, however, an easy task. Some
topics are simply not researchable for a number of reasons. Others may be too vague to
conceptualize and operationalize. It is therefore, not easy to focus on a topic which is
neither too narrow nor too broad. The research topics should be properly assessed and
rated for their selection.

A well- written proposal is a blueprint for the research investigation. It provides an

argument for the proposed study. It needs to explain the logic behind the proposed study,
rather than simply described or summarize the study, and to do so in a way that even non-
specialists will understand. The researcher should explain what he/she wants to do.
Proposals, which are not well- written and well-justified are often rejected. It should also be
remembered that a proposal is not a place to display the knowledge of the literature on the
proposed topic. This may irritate the evaluators.

54
Research proposals vary according to the study and when it is to be submitted to different
agencies. The length of the proposal is not important. What is important is the researcher’s
thinking. Generally, a research proposal follows the general format of a journal article but
headings of various sections may be different according to the subject; but following steps
are generally followed in preparing a research proposal:

1. Background of the study: - A researcher may select any topic according to his/her
interest and experience. But the researcher should be familiar with the background and
fundamental concept of the research topic which he/she has selected. It means, the
researcher should explain the answers of such questions as- What is the problem? How
the problem emerged? What are the consequences of the problem? And so on. The
detail description about the researchable problem should be mentioned by the
researcher in this section.
2. Statement of the problem: - The problem of research topic is expressed in a declarative
statement but it may be in question form. The problem must be stated in such a form
that it clearly tells about the major goals of the research. Beside this, the researcher
must mention why it is worth the time, effort and expense required to conduct the
proposed research. In other words, the proposal written should not only mention the
problem clearly but must also demonstrate its significance. For example, what type of
social theory can be formulated through the research? What type of benefit can achieve
the nation? Or what type of social problem can be solved through this research etc.
3. Objective of the study: - Generally, the objectives are vided into two categories like
general objective and specific objective. The objective should be mentioned by a
researcher in his/her research proposal because no research activity is carried out
without any objective. It means, a researcher should be able to define the main aim of
topic selection, its impact in the society or its contribution to the nation. The proposed
objectives should also be justified after the completion of research which must be
included in the research report.
4. Importance of the study: - It should be remembered that a research activity may find
out a solution for a social problem. In this sense, the researcher should be aware that
what significant change will be brought out by a research finding in his surroundings. In
other words, a researcher should mention the significance or importance of his research
and tentative findings. So, the importance of study should also be mentioned in the
research proposal which may attract the donors and other concerned parties. It means,
which ethnic group, society, class, group or community will be benifitted by a particular
activity should be clarified.
5. Literature review: - The research proposal should include a more extensive review of
relevant literature. An effective relevant literature includes those studies which have
been clearly reported and are closely related to the present problems. This step ensures
that the researcher is familiar with what is already known, what is still unknown that is
to be verified and tested. Moreover, it also helps to eliminate the duplication of what
has already been done and provides background for useful suggestions for further
investigations. In search of related literature, the researcher, among others, should
concentrate upon similar but completely executed studies, design of the study, sampling

55
 method, population sample, variable defined and controlled and recommendations etc.
for further research.
6. Hypothesis: - The research proposal should include the major hypothesis to be tested.
Some minor hypothesis if any, should also be formulated. Since research hypothesis is a
tentative answer to a question, it is important that the hypothesis should be formulated
before data are gathered. In fact, formulation of hypothesis is such a step which clarifies
the nature of the problem and also underlying logic of the research investigation. A
hypothesis should be reasonable with known facts in the concerned area, testable and
able to state in simplest possible terms.
7. Methodology: - It is an important part of research proposal through which a researcher
can enter into the process of data collection and analysis. It includes three sub sections
like – subject, procedure and data analysis. The total number of subjects derived from
the population from which subjects are to be selected. The total number of subjects
desired from the population and how they will be selected are generally indicated in this
sub section. The procedure subsection outlines the details of research plan; or it
outlines in detail about what will be done, how it will be done, what data will be needed
and what data gathering devices will be used etc. And the data analysis subsection
outlines the details of methods of analyzing data by different statistical techniques.
8. Time schedule: - An effective proposal must have a clear time schedule in which the
entire project should be divided into manageable parts and probable budgeting. Such
steps help the researcher in budgeting the time and energy effectively, systematizing
the study and minimizing the tendency to delay the completion of research activity.
9. Expected results: - A good research proposal should also include the possible or
expected results as far as possible. Although in some cases it may prove to be more
difficult task for the researcher to spell out the expected results. This section should
include a brief discussion about the possible results of the research as well as the
alternative results which will be compared with the hypothesis during data analysis
procedure.
10. References: - The references should include the names of the authors along with their
details of the publication of their research work. It should be more or less like that same
section as it would be submitted with the final research report. Sometimes the
researcher may mention the used references in every page as footnote, but it is not a
rule.
11. Appendix: - A research proposal completes with an appendix which should include a list
of all materials that are to be used in the study, such as – a copy of the test or scale
used, map, instructions, questionnaires etc.

56
 Chapter- ix

Research Report

Research report is a written, integrated and systematic representation of the

investigation, facts or evidences, findings, conclusion and suggestions or
recommendations of the research works. The objective of the research report is to
communicate the exact detailed result of the research study to the readers and
evaluators. Presentation of research findings in the form of a report is the necessary
part of the research process. Any research inquiry begins with an idea and ends with a
report. A report is a detail description of what has been done and how it has been done
with respect to a particular area or topic of research. A report may be addressed to the
experts in the field for a critical evaluation of the achievements made. A research report
may be helpful to throw some new light in the selected theory of field of inquiry.

Types of Report:

The types of research reports are not limited that there various types of reports such as
formal or informal, written or oral, internal or external, short or long, technical or
popular, analytical or informal etc. The length and form of research reports are largely
depend upon the problems at hand. For example the reports prepared by governmental
bureaus, special commissions and similar other organizations are very comprehensive
reports on the issues involved. However, for thesis assignment purpose, the reports are
categorized into descriptive and analytical form.

According to UN statistic Office, there are mainly three types of reports, which are:

(1) Preliminary report: - A preliminary report giving the available data of current interest
is required to present as soon as possible. Such results may relate to characteristics
of the survey population and variables. The report contains a brief statement about
survey method, size of the sample used, method of selecting sample and the
limitation of the data.
(2) General report: - A general report includes information on the following:
- Statement of purposes of the survey
- Description of the coverage
- Nature of the information collected
- The method of data collection
- Numerical results
- Time of the data collection
- Time taken for the fieldwork
- Accuracy
- Cost
- Assessment of the fulfillment of the purpose of survey
- Sponsoring organization

57
 - References
(3) Technical report: - The technical report gives emphasis on methodological part of
the study and findings. The report should include the following information:
- List of population
- Sample design
- Personnel and equipment used
- Statistical analysis and computational procedure
- Control of sampling errors
- Comparison with other sources of information
- Cost analysis
- Efficiency of sample design
- Observation of technicians

Essential outline of Research Report

A format or layout of research report includes the contents of research report. There is no
uniformity about the format of research report. The structure varies from person to person and
place to place. But in general, the format of research is divided into the following three parts:

PART – 1

A. Title page: - The title page is the first page of report and it should carry a clear and
descriptive title of the research. The entire title should be typed in all capital letters. All
the items in the title page should be centered between the margins of the page. The
writing should be in an inverted pyramid style.
B. Acceptance letter: - It includes the advisor’s signature along with the title and name of
the researcher.
C. Acknowledgement or preface: - This heading may include reasons why, in the first place,
the topic was selected by the researcher. It may explain about history, scope,
methodology or writer’s opinion of the place of study in the field of knowledge and how
it will provide a basis for the report writing. The researcher also expresses his/her
gratitude to the concerned persons under this topic.
D. Table of contents: - The purpose of table of contents is to provide an outline of the
content of the report. It may contain only a list of chapters and their appropriate roman
numerals, followed by page numbers on which each chapter begins.
E. List of tables and figures: - If tables and figures are included in the report, they are listed
in separate pages with full titles worded exactly as they appear in the text. Arabic
numerals are generally used for identifying tables and figures.
F. Abbreviations: - In the references, whether in the form of footnotes or literature cited
or bibliographical notes, it is possible to use abbreviations to avoid writing and typing
long name in full. The list of abbreviations should appear before the beginning of the
main text.

58
PART – II THE TEXT

In a thesis, the text may comprise chapters and their divisions. The division should be logical
to make the contents meaningful. The text includes the following chapters and headings:

Chapter -1

1. Introduction: - Introduce the subject by highlighting its special features in about two or
four paragraphs/ pages. The introduction should interest the reader in the subject
matter of research. It must not be dull, confused and aimless.
1.1. Statement of the problem: - A clear statement of the nature and importance of
the problem with specific question to be answered or hypothesis to be tested,
consideration of significance of the problem and its historical background is also
appropriate. The key questions and the location of the problem in the theoretical
context of the concerned subject should be specified.
1.2. Objective of the study: - The objective of the research study is to be listed in
clear and distinct form. The purpose of this study was ‘…………………….’ Is to be stated. A
brief explanation of the purpose may be made in case of multi-purpose study.
1.3. Organization of the study: - A brief textual outline of each of the five or more
chapters should be included.

CHAPTER – II

2.1. Review of literature: - This heading summarizes the current status of research works
already done. It means, previous research studies are abstracted and significant writings
of authorities in the area under study are reviewed. Such a review provides a
background for the development of the present study. A brief summary, indicating areas
of agreement or disagreements in findings or gaps in existing knowledge should also be
included in this section.

2.2. Justification of the study: - The significance of the problem, the contribution which
the study is expected to be made to the theory, its practical importance and the national
relevance should be specifically indicated.

2.3. Scope of the study: - The scope of the study point out the exact coverage reported
upon, and position of the research within its larger context.

2.4. Conceptual framework: - In this heading, various concepts proposed to be used in a

research requires to be stated; definitions or special meanings of all important terms so
as to enable the readers to understand the concepts used in the investigation.

59
CHAPTER - III

1.1.1. Methodology: - In this section, an opening paragraph linking the purpose, hypothesis
or research question and format is to be included. The methodology describes the
research design, method of data collection, variables and control employed,
reliability of instrument selected and the statistical tools and procedures used in the
analysis. Such as:
1.1.2. The research design:- It describes the design used in research activity such as:
exploratory, historical, survey, case study, experimental or semi experimental etc.
with a graphic model.
1.1.3. Sampling procedure: - It describes the sampling procedure of data collection such
as : simple random, stratified, multistage, purposive etc.
1.1.4. Data gathering procedures: - It indicates the sources of data and how they were
gathered, such as interview, observation, questionnaire, schedule etc.
1.1.5. Variables and measures: - The variables set in first chapter are defined operationally
in terms of quantitative measurement. In this section, sub sections may be made for
independent, dependent and intervening variables.
1.1.6. Statistical procedures: - In this section, the basic and descriptive statistical
techniques of data analysis such as proportion, percentage, mean frequency,
standard deviation, correlation and chi-square test etc. are used.
1.1.7. Data processing procedures: - A brief description about the data coding sheet and
computer programs can be presented but it is not compulsory.
1.1.8. Limitations of the study: - Since all research designs have certain limitations; so, the
limitations regarding the coverage of the frame is to be illustrated.

CHAPTER – IV

4.1. Presentation of data: - This is the heart of the research report in which an organized
presentation of research results and each major division of the problem should be presented in
a separate chapter. The chapter generally covers presentation of the arguments,
documentation, ideas, concepts, interpretations and findings. The chapter should include a
discussion of the issue or part of the problem investigated the evidence used in its solution.
Through textual situation, tabular and graphic devices, the data are critically analyzed and
interpreted in detail. The general guidelines of presentation of the data are as follows:

- Present the qualitative data such as age, sex, income, educational level etc. in tables using
categories of frequencies, percentage of range, means and standard deviation.

- Do not present the percentage without frequencies, and do not present means without
standard deviation.

- For two quantitative variables establish the cause- effect relationship.

- Select the proper statistical test for analysis.

60
- Test hypothesis using appropriate statistical methods.

CHAPTER –V

SUMMARY CONCLUSION AND RECOMMENDATION

5.1. Summary: - Present the summary of the findings of the research in one or two paragraph.

5.2. Conclusion: - In this section, the conclusion is presented as a separate heading. It is also
presented in two to three paragraphs.

5.3. Recommendations: - The researcher should aim to give some hints to future research
scholars because no research is an end itself. The researcher should be able to give directions to
the future researchers which the investigator has gained during the investigation. In case of the
research of social problem, the researcher should provide the suggestions to correct the
weaknesses.

PART – III

A. Bibliography: - The bibliography must include all published or unpublished sources

mentioned in the text or footnotes. By listing each reference in the correct form avoids
the extra time involved in finding the references. The general entries in bibliography
should be made in the following order:
- Name of the author starting from last name
- Year of publication in bracket
- Title of the article or work
- Name of the journal or publication
- Place of publication
- Page number

Example : Kerlinger, F. N. (1983), The Foundation of Behavioral Research, New Delhi,

Surjeet Publication, p: 108.

The references are to be presented sequentially as they appear in the text,

bibliography should be presented in the following group order:

- Books
- Journals/ articles
- Newspapers
- Published documents
- Unpublished documents

61
 B. Appendix: - Appendix is used for additional materials which has not been found place in
the main text. The complex tables, original data schedule, questionnaire, interview
forms, and other materials used are placed in appendix. If more than one appendix is
necessary, each part should be designated as appendix – A, B, C etc. using Arabic
numerals.

Use of Abbreviations:

Several abbreviations are used by the researcher so as to minimize the space. Some of the
commonly used abbreviations are as follows:

anon : anonymous

ante : before

art. : article

bk. : book

bull. : bulletin

c. f. : compare

ch. : chapter

col. : column

ed. : editor/edition

ed. Cit. : edition cited

e.g. : exemplia gratia (for example)

et.al. : et alii (and others)

f. : and the following

fig. : figure

fn. : Footnote

ibid. : in the same place (for page number)

id. : the same

62
I or II : line (s)

N. B. : nota bene (note well)

n. d. : no date

n. p. : no place

n. pub. : no publisher

o .p. : out of print

p. or pp. : page (s)

viz. : videlicet (namely)

vol. :volume

vs. : versus , etc.

DATA ANALYSIS

Preparing and presenting data:

The presentation of data is the basic organization and classification of the data for analysis.
After data collection is completed, the data will be in the form of raw data. Thus, it is necessary
to arrange the data so that it makes some sense to the researcher which can later be presented
to the readers of the thesis. Different types of data require different methods of summary and
presentation. There are a number of methods, which can be used to simplify the data. The
easiest way to understand data is by examining it in charts, graphs and tables.

Organization and processing of data require knowledge of some technical methods. There is a
definite sequence for analyzing data. The overall process of analyzing data can be viewed as
involving a number of separate and sequential steps. The activities in data processing include
editing, classification, coding and tabulation. Separate and brief description of each process has
been made as follows:

(i) Editing: - Editing is the first step in data processing. It implies checking and
correcting the data gathered from primary sources in a systematic way to ensure

63
 their accuracy and completeness. The purpose is to detect omissions, errors, and
inconsistencies (variations) in responses. Editing should be done as soon as possible
after the data have been collected. The editor of data should look at each collection
form with respect to three criteria, such as – completeness, consistency (uniform)
and accuracy.
(ii) Coding: - Coding is the means of deciding how the responses are going to be put
together in a frame so that they can be entered in to the computer or the manual
data sheets. It is the process, which includes identifying and categorizing of each
response on a data collection instrument with a designed symbol. The purpose of
coding is to facilitate the transfer of data from data collection instrument in to
computer readable form. Thus, this is the process of assigning codes to responses
after the data are collected. Sometimes, coding sheets are used first to enter the
data from the questionnaire, and then key in the data.
(iii) Classification: - Classification refers to dividing of the data into different categories,
classes, groups or heads. Analysis of data requires that it should be grouped into
categories or classes. Classification becomes necessary when there is diversity in the
data collected for meaningful presentation and analysis. Hence, through
classification the complex and scattered data are organized into concise and logical
forms. This allows the researcher to make comparisons and generalizations.
(iv) Tabulation: -Tabulation is simply the counting of the number of responses in data
categories. It is the process of transferring classified data from data gathering tools
to the tabular form in which they may be systematically examined. Tabulation
summarizes raw data and displays them in compact form for further analysis.
Most tabulation work is simple. It converts data into frequency distribution. This
types of tabulation consists of a count of the number of responses that occur in each
of the data category. The other type of tabulation is known as cross- tabulation. This
method utilizes the simultaneous counting of number of observation that occurs in
each of the data category based on two or more factors. Where a small sample is
used, and limited analysis is required, the hand tabulation is quite useful. However,
when sample size is large and the complexity of the required analysis is needed,
there comes a point at which computer tabulation becomes more productive and
efficient.

Summarizing data : Tables, graphs and charts: -

(i) Tables: - In tabulations, data are arranged in the forms of tables, for facilitation the
statistical and mathematical operations. The choice is made largely on the basis of
size and type of study, alternative costs, time pressure and availability of computers.
A table possesses the following components, such as- Table number, Title of the
table, columns and rows, head note and footnotes etc. Tables are of two types
which are as follows:
(a) Simple table: - Simple table is made on the basis of just one quality or
characteristics. Examples of such tabulation are the classification of development

64
 region on the basis of population, distribution of students on the basis of subject
s of the study etc. Such as:
Marks obtained by 100 students in research

Marks No. of students

0-10 14
10-20 26
20-30 30
30-40 20
40-50 10

Total 100
(b) Complex table: - This is formed on the basis of more than one quality or
characteristic- e.g. distribution of students on the basis of sex and marks
obtained etc. If complex table is based on two qualities, it is called a two-way
table. If it is based on three qualities, it is called three-way table and if there are
more than three qualities it is called manifold table. Such as :

Marks obtained by 100 students in research methodology

(sex- and residence-wise)

Marks No of students
Male Female Total
Boarders Day Total boarders Day Total Boarders Day Total
scholars scholars scholar
s
0-10 3 6 9 3 2 5 6 8 14
10-20 7 6 13 3 10 13 10 16 26
20-30 10 8 18 8 4 12 18 12 30
30-40 4 8 12 5 3 8 9 11 20
40-50 5 1 6 3 1 4 8 2 10
Total 29 29 58 22 20 42 51 49 100
(ii) Graphs: - Another important method of representing statistical facts and
information is the graphical representation. It is very commonly used procedure and
may be applied to any situation where a lagre mass of data are to be dealt with such
a representation is widely used in the field of economics , commerce , sociology and
many other fields of science and humanities. When the data is presented in the
graph, it is readable even by the public.
Graphs are of various types and it varies from the nature and type of data. It may be
a simple graph where absolute figures are plotted. A graph representing single
variable consists of one curve only. For more than one variable, the number of
curves will be shown separately by using different types of curves or different colors.

65
Eg.

Year Budget of Govt. of Nepal

(in million Rs.)
1963-64 24.5
1964-65 28.8
1965-66 36.2
1966-67 37.2
1967-68 43.5

Budget of the govt. of Nepal (in million Rs.)

50

45

40

35

30

25

20

15

10

0
1963-64 1964-65 1965-66 1966-67 1967-68

66
 Example of Two variable graphs:

Year Budget of Education Ministry

Total Govt. budget (in million Rs.) (in million Rs.)
1963-64 100.00 45
1964-65 107.3 57
1965-66 135.4 61
1966-67 161.2 69
1967-68 197.2 78

250

200

150

100

50

0
1963-64 1964-65 1965-66 1966-67 1967-68

67
 (iii) Charts and diagrams: -
Diagrammatic representation of information has now become a popular way to
communicate findings to the readers. Data presentation in the form of charts and
diagrams can provide a quick and concise insight into the subject under
investigation. The value of good charts and diagrams is that they add significantly to
the reader’s ability to understand and follow the report. The choice of charts,
diagrams, or graphs will be determined by the research questions and objectives.
The following few examples will explain the application of charts, graphs and
diagrams:

-
Bar charts and multiple bar charts are used to show the highest and lowest
values for the variables.
- Pie charts are used to show the proportions of occurrences of categories or
values.
- Line charts and time series graphs are used to show the trends of variables.
- Scatter diagrams are used to show the relationship between cases for two
variables.
Some common types of charts and diagrams and their examples have been presented as
follows:

(a) Simple and multiple bar charts: - These are the simplest and popular diagrams in use. It
consists single or multiple bars of equal width. The length of the bars represents
different values of variable. The bars may be vertical or horizontal, but we generally use
vertical bare because they are more attractive and easier to compare.
Example: Draw a simple bar diagram to represent the following data:

Year 1951 1961 1971 1981 1991 2001

Population (in Million) 9 10 12 15 18 23

68
 25

20

15

population
10

0
1951 1961 1971 1981 1991 2001

Multiple bar diagram:

Data:

Year sales (000Rs.) gross profit (000RS.) net profit (000RS.)

1995 100 30 10

1996 120 40 25

1997 130 50 30

1998 150 60 50

69
 Sales, gross profit and net profit (for the years 1995-98) (in ‘000’ Rs.)

160

140

120

100

sales
80
gross profit
net profit
60

40

20

0
1995 1996 1997 1998

Beside multiple bar diagram, sub divided diagram can also be used which represents the
figure of different characteristics in a single bar. The magnitude of ea variable is divided
into different parts. In other words, total magnitude is divided into the sub
characteristics and figures are presented in terms of rectangles or bars.

(b) Pie diagram/chart: - A pie diagram is a circular diagram in which sub divisions of a total
into its components may be easily exhibited. Thus, more than one variable may be
presented in a circle. In such a diagram, a further sub division of the sub divided values
of the total is also possible which makes this diagram that most commonly used one.
One can construct the pie diagram expressing each of the component value the s as a
percentage of the respective total and express the percent into angle by 1%= 360 0/100=
3.60, The percentage of component parts are multiplied by 3.6 0 to express in angles and
draw a circle of appropriate radius using an appropriate scale.
Example: Represent the following data in a pie diagram:

Cost of construction of a business house at Itahari

Items Expenditure Angle in degree

Labor 25% 25*3.6=900

70
 Bricks 30% 30*3.6=108

Cement 20% 20*3.6=72

Iron 10% 10*3.6=36

Timber 10% 10*3.6=36

Others 5% 5*3.6=18

Total 100% 3600

%expenditure

Labor
Bricks
Cement
Iron
Timber
Others

Statistical Analysis

(i) Descriptive analysis: -

Descriptive statistics is the term given to the analysis of data that helps describe, show or
summarize data in a meaningful way such that, for example, patterns might emerge from the
data. Descriptive statistics do not, however, allow us to make conclusions beyond the data we
have analyzed or reach conclusions regarding any hypotheses we might have made. They are
simply a way to describe our data.

71
 Descriptive statistics are very important, as if we simply presented our raw data it would be
hard to visualize what the data was showing, especially if there was a lot of it. Descriptive
statistics therefore allow us to present the data in a more meaningful way which allows simpler
interpretation of the data. For example, if we had the results of 100 pieces of students'
coursework, we may be interested in the overall performance of those students. We would also
be interested in the distribution or spread of the marks. Typically, there are two general types
of statistic that are used to describe data:

 Measures of central tendency: these are ways of describing the central position of a
frequency distribution for a group of data. In this case, the frequency distribution is simply
the distribution and pattern of marks scored by the 100 students from the lowest to the
highest. We can describe this central position using a number of statistics, including the
mode, median, and mean.
 Measures of spread: these are ways of summarizing a group of data by describing how
spread out the scores are. For example, the mean score of our 100 students may be 65 out
of 100. However, not all students will have scored 65 marks. Rather, their scores will be
spread out. Some will be lower and others higher. Measures of spread help us to
summarize how spread out these scores are. To describe this spread, a number of
statistics are available to us, including the range, quartiles, absolute deviation, variance
and standard deviation.

When we use descriptive statistics it is useful to summarize our group of data using a
combination of tabulated description (i.e. tables), graphical description (i.e. graphs and charts)
and statistical commentary (i.e. a discussion of the results).

(ii) Inferential Analysis: -

Whilst descriptive statistics examine our immediate group of data (for example, the
100 students' marks), inferential statistics aim to make inferences from this data in
order to make conclusions that go beyond this data. In other words, inferential
statistics are used to make inferences about a population from a sample in order to
generalize (make assumptions about this wider population) and/or make predictions
about the future.

For example, a Board of Examiners may want to compare the performance of 1000
students that completed an examination. Of these, 500 students are girls and 500
students are boys. The 1000 students represent our "population". Whilst we are
interested in the performance of all 1000 students, girls and boys, it may be
impractical to examine the marks of all of these students because of the time and
cost required to correlate all of their marks. Instead, we can choose to examine a
"sample" of these students and then use the results to make generalizations about
the performance of all 1000 students. For the purpose of our example, we may

72
 choose a sample size of 200 students. Since we are looking to compare boys and
girls, we may randomly select 100 girls and 100 boys in our sample. We could then
use this, for example, to see if there are any statistically significant differences in the
mean mark between boys and girls, even though we have not measured all 1000
students. For inferential analysis, some statistical techniques like correlation,
coefficient variation, chi-square (x2) test, T-test, F-test, Z-test etc. are used.

Parametric and non- parametric analysis:

Parametric analysis is a description and examination of relationship between or

within variables making certain assumptions regarding population parameters.
Parametric tests make some assumptions regarding the population is normally
distributed, and if the population has homogeneity characteristics and less variance.
So, parametric tests can be conducted under the following conditions:

(1) The variables are measured at least in the interval scale

(2) The sample size must be greater than twenty
(3) The sample must be drawn from a normal probability distribution.

Parametric tests can be done using three statistical methods like- normal Z- test, T-test and F-
test.

Non parametric tests do not make an assumption about the parameters of the population and
thus do not make use of the parameters of the distribution. Under non-parametric or
distribution free tests, we do not assume that a particular distribution is applicable. For
example, while testing the two training method, say I and II, for determining the superiority of
one over the other, if we do not assume that the scores of the trainees are normally distributed
or that the mean score of all trainees taking method I would be a certain value, then the testing
method is known as non- parametric method. Non- parametric tests can also be used in
nominal and ordinal scales. The bases of non- parametric analysis are as follows:

(i) The sample size can be less than twenty.

(ii) No assumptions made regarding the distribution of population from where sample is
drawn.
(iii) Measurement of variable is mostly ordinal.

There are various methods of non- parametric test and among them Chi-square (x 2) test is most
popular.

73
74