Unit Five

Sampling Design

BY: Kassa T. (MA)

Shawel A. (MBA)
1
CONTENTS
 Census vs. Sample Survey
 The Need for Sampling

 Characteristics of a Good Sample

Design
 Steps in Sample Design

 Types of Sampling

 Sampling Error and Sampling

Bias
2
 Sample Size Determination
DEFINITION OF CONCEPTS
 Population (finite or infinite)
refers to any collection of specified
group of human beings or of non-
human entities such as objects,
educational institutions, countries,
states, clubs, industries etc.
 A complete enumeration of all items

in the population is known as a

census inquiry. 3
 Sampling design is a definite plan for obtaining a
sample from a given population.
 Sampling Frame: - A list of every individual in the

population - Frame is either constructed by the

researcher or some existing list of population is
used
 Sampling frame should be a good representative of

the population and as far as possible free from (i)

Incompleteness (ii) Inaccurateness
(iii)Inadequateness (iv) Out-of-date

4
A sample (n) is a subset of a
population (N) to which the
researcher has selected with a due
care and intends to generalize the
results of the study to the entire
population.
Survey conducted on the basis of

sample is sample survey

5
EXAMPLE:
Let’ssay you want to find the
average GPA of a student at your
university.
Your university has 20, 000
students and you select 100
students and ask them their GPAs.
What is your population (N) ?
 What is your sampling frame?
 What is your sample (n)?
6
WHY WE NEED SAMPLING?
Sampling makes possible the study of
a large, heterogeneous (different
characteristics) population.
The population to be studied maybe
too large or unlimited that it is almost
impossible to reach all of them.
Sampling makes possible this kind of
study because in sampling only a small
portion of the population maybe involved
in the study, enabling the researcher to
reach all through this small portion of the
7
population.
Sampling is for economy.
Research without sampling may be too costly.
Sampling reduces the study population to a
reasonable size that expenses are greatly
reduced.
Sampling is for speed .
Research without sampling might be too time
consuming.
Sampling is for accuracy.
If it takes too long a time to cover the whole
study population, there maybe inaccuracy. The
research must be finished within a reasonable
period of time so that the data are still true, 8
valid and reasonable.
DISADVANTAGES OF SAMPLING

If sampling is biased, or not

representative, or too small, the
conclusion may not be valid and
reliable.
If the population is very large and
there are many sections and
subsections, the sampling procedure
becomes very complicated.
If the researcher does not possess
the necessary skill and technical
knowhow in sampling procedure. 9
CHARACTERISTICS OF A GOOD
SAMPLING DESIGN
 Truly representative
 Having small sampling error

 Economically viable

 Systematic bias is controlled (in a better way)

 Results can be applied to the population in general

with a reasonable level of confidence ⇒reliability

 Optimum size (adequately large)

 Similar to population-should have all the

characteristics that are present in the population

10
STEPS IN SAMPLING DESIGN
 Defining the population – target population
 Listing the population – sampling frame

 Selecting a representative sample – based on

appropriate method (probability or non-

probability)
 Obtaining an adequate sample size –
For statistical measurement > 30 sample size (Stutely 2003)
or
 Use this formula n = ___N_______
1 + N(e2)
(Pagoso , et al. p.46)

11
HOW TO APPLY THE FORMULA
 Determine the size of the population.
 Decide on the margin of error. (As much as possible
the margin of error should not be higher than 5%.
Probably 3% is an ideal one)
 Use the formula n = ___N_______
1 + N(e2) (pagoso , et
al. p.46)

n = sample size
N = the size of the population
e = the margin of error
 Compute the sample proportion by dividing the sample
obtained by the population.
12
EXAMPLE,
Population is 5,346
Margin of error is 3%
Using the formula n = ___N______
1 + N(e2)

n = 1+ 5346(.03) 2
n = 920
Sample proportion (%) = 920 /
5346
13
= 17%
There are no fixed rules in determining
the size of a sample needed. There are
guidelines that should be observed in
determining the size of a sample.
 When the population is more or less
homogeneous and only the typical, normal, or
average is desired to be known, a smaller sample
is enough. However, if differences are desired to
be known, a larger sample is needed.
 When the population is more or less

heterogeneous and only the typical, normal or

average is desired to be known a larger sample is
needed. However, if only their differences are
desired to be known, a smaller sample is
sufficient. 14
 5.5. TYPES OF SAMPLING
 There
are different kinds of sampling designs
depending on:
 the types of study being conducted and
 the kinds of conclusions the researcher would like to
be able to draw from the study results.
 Generally speaking, there are two broad
categories of sampling. These include the
following:
- Probability sampling and
- Non-probability
sampling 15
TYPES OF
SAMPLING

16
1. PROBABILITY
SAMPLING
Probability sampling (also called
random sampling) is based on the
concept of random selection.
In this type of sampling the units of

the population are chosen by

means of certain procedures which
ensure, that every members of the
population has one fixed probability
of being included in the sample.
17
 Probability sampling is the most preferred types of
sampling because of the following peculiar
characteristics:
The units of the population are not selected
based on the discretion of the researcher.
Each unit in the population has some known
probability of entraining in the sample.
Weights appropriate to the probabilities are
used in the analysis of the sample
The process of sampling is automatic in one or
more steps of selection of units in the sample.

18
A) SIMPLE RANDOM SAMPLING

 this type of sampling is one in which every one in

the population of the inquiry has an equal chance
of being selected to be included in the sample.
 also called the lottery or raffle type of sampling.
 this may be used if the population has no
differentiated levels, sections, or classes.
 main advantage of this technique of sampling is
that, it is easy to understand and it is easy to
apply too.
 disadvantage is that, it is hard to use with too
large a population because of the difficulty
encountered in writing the names of the persons19
involved.
B) SYSTEMATIC RANDOM
SAMPLING
 In systematic sampling, a researcher
generally starts with a list in which all
the N units of the population are listed
in alphabetic or some other order.
 To select a sample of size n, he has to

select a unit at random from the first K

units of the list and the every Kth
subsequent unit is selected.
 The number K is so chosen that NK is

less than or equal to N (or K = N/n ) 20

SYSTEMATIC…
 While this approach is simple and less
costly than simple random sampling
technique, the researcher may run the risk
of omitting key components from his
sample, and at times, his findings might
become unreliable.

 systematic random sampling could be

effective if all elements of the universe are
ordered in a manner representative of the
total population i.e. the population list in 21
random order.
 C) STRATIFIED SAMPLING
 Ifa population from which a sample is to be
drawn constitutes a heterogeneous group,
stratified sampling is generally applied in
order to obtain a representative sample.
 A stratified sample is obtained by

separating the population elements into

non-overlapping groups, called strata.
 The usual stratification factors include sex,

age, socio-economic status, educational

background, academic rank, residence
(urban or rural) occupation, religion, caste,
general intelligence and so on. Eg. …
22
 STRATIFIED…
 Since each stratum is more homogeneous than
the total population, we are able to get more
precise estimates for each stratum and by
estimating more accurately each of the
component parts; we get a better estimate of
the whole.
 Besides, the application of this procedure saves

a considerable amount of time and money.

 In short, the use of stratified sampling is more

economical, reliable and unbiased than that of

systematic random sampling technique.
23
 STRATIFIED…
 The efficiency of the stratified random sample
depends upon the allocation of samples size
to strata.
 The simplest and most common system of

allocation of sample units among strata is in

proportion to the sample size of the strata.
 Illustration….

24
D) CLUSTER SAMPLING
A cluster sample is a type of random
sample in which sampling units is a
collection, or cluster, of elements.
 It involves division of elements of a

population into groups and then

randomly select some of these smaller
groups (usually called clusters) with
the ultimate sample consisting of all
(or parts of) units in these clusters.
25
CLUSTER…
 This type of sampling is applied when:
 the size of the study population
extremely large or infinite,
a list of population members does not
exist,
the geographical distribution of the
members is scattered or
when the selection of individual
members is not convenient for a number
of reasons.
26
To illustrate….
CLUSTER…
Unlike stratified sampling, in
which every stratum is
sampled, cluster sampling
samples among groups or
clusters.
Besides, in cluster sampling

the exact sample size may not

be known before the sample is 27

selected.
 E) MULTI-STAGE SAMPLING.
 This is a further development of the cluster
sampling.
 This technique is used for large scale
surveys or inquiries extending to a
considerably large geographical area like
an entire country or nation.
 In this case, the researcher may have to
use two, three, or four stage sampling.
 The first stage may be to select large
primary sampling units such as regional
states, then administrative zones, then
woredas, and finally certain families
within woredas.
28
 Illustration …
In general,
 Almost all random sampling techniques
assume that you have a complete and
accurate list of all members of the population
from which you wish to select you sample.
However, in reality, this is rarely the case.
 For example, alumni files are notoriously

incomplete. Even rosters of currently enrolled

students always include a few students with
missing, incomplete, or outdated addresses.
Surveys administered to a class in person will
miss absent students.
29
30
31
 2. NON-PROBABILITY SAMPLING
 In non-probability sampling, the units are
selected at the discretion of researcher.
 Such samples drive their control from the

judgment of the researcher.

 Some of the disadvantages of non probability

sampling include the following:

No confidence can be placed in the data
obtained from such samples as they do not
represent the larger population. Therefore,
the results obtained cannot be generalized
for the entire population. 32
 The selective sample is based on
convenience affects the variance within
groups as well as between groups and so
sampling error of such samples cannot be
determined.
 Non-probability sampling depend exclusively

on uncontrolled factors and researchers

insight, and there is no statistical method
determine the margin of sampling errors.
 Sometimes such samples are based on an

obsolete frame which does not adequately

cover the population.
33
Theobvious advantage of non-
probability sampling is that :
itis much less complicated,
much less expensive,
may be done on a spur-of-the-moment
basis
convenient in the situations when the
sample to be selected is very small and
the researcher wants to get some idea of
the population characteristics or of the
problem using well-informed members in a
short time. 34
 The non-probability sample may
prove perfectly adequate if the
researcher has no desire to
generalize his findings beyond the
sample, or if the study is merely a
trail run for a larger study.
 If the researcher plans to repeat the

study at a later date, he may initially

be more interested in perfecting the
questionnaire that in the sample and
may find a non-probability sampling
adequate. 35
Thereare five basic types of
non-probability sample, which
include:

Convenience sampling,
Quota sampling,
Dimensional sampling,

Purposive sampling, and

Snowball sampling.

36
A) CONVENIENCE SAMPLING

 In convenience or accidental sampling,

the investigator merely chooses the
closest live persons as respondents.
 A common example is “captive audience”

sampling, as in the use of introductory

social-science students as questionnaire
respondents.
 In general, the availability and willingness

to respond are the major factors in

selecting the respondents. 37
 B) QUOTA SAMPLING
 Quota sampling is the non-probability
sampling which is equivalent to stratified
sampling with added requirement that each
stratum is generally represented in the sample
in the same proportion as in the entire
population.

 When stratified random sampling is

impractical to use because of difficulty of
getting complete list of the units in the strata
of a population, quota sampling becomes 38

appropriate.
 Inquota sampling one first decides which
strata may be relevant for the study to be
conducted e.g.
 Republicans and Democrats for a study of
voting behavior in USA,
 Blacks, Whites, and Chicanos for a study of
race relation.
 Thenthe investigator sets a quota for
each stratum that is proportionate to its
representation in the entire population

39
C) DIMENSIONAL SAMPLING

 Dimensionalsampling is basically a
multidimensional form of quota sampling.

 The idea is to specify all dimensions

(variables) of interest in the population
and then to make sure that every
combination of these dimensions is
represented by at least one case.

40
 For
efficient use of such a method; you
must note the following points:
 Explicitly delineate the population to which
you eventually wish to generalize,
 Spell out what appear to be the most
important dimensions along which the
members of this population vary and develop a
typology that includes the various
combinations.
 Use this typology as a sampling frame for
selecting a small number of cases from the
population, typically drawing one case from
each cell of the typology (Amold, 1970 as cited41
in Bailey, 1982.98)
 This method is designed for studies in
which only a small sample is desired so
that each case drawn can be studied in
more detail than is possible in a large
scale study.

 Itis designed to overcome the danger of

missing important variables in selection of
small application of this method as
follows; 42
D) PURPOSIVE SAMPLING
 Inpurposive or judgmental sampling, the
researcher uses his own judgment about
which respondents to choose, and picks
only those who best meet the purposes on
the study,
 The obvious advantage of purposive or

deliberate sampling is that the research

can use his research skill and prior
knowledge to choose respondents.

43
 E) SNOWBALL SAMPLING
 the term, “snowball” stems from the analogy of
a snowball, beings small but becomes bigger
and bigger as it rolls downhill.
 Adapted from such a concept, a snowball

sampling has gained popularity among scholars

conducting observational research and
community studies.
 Conducted in stages.
 Inthe first stage a few persons having requisite
characteristics are identified and interviewed.
 The second stage involves interviewing these
persons, who in turn lead to still move persons who
can be interviewed in the third stage, and so on. 44
45
5.6. Sampling Error and Sampling
Bias

 Sampling studies are subject to sampling

and non sampling errors which are of a
random and/or of a constant nature.
 The errors created due to sampling and of

which the average magnitude can be

determined are called sampling errors,
while others are called sampling bias.
 These concepts are discussed in detail

below.
46
A) SAMPLING ERRORS
 These are errors that are created because of chance
only. Although a sample is properly selected, there
will be some difference between the estimates
obtained from the sample (sample statistics) and
the actual value in the population (parameters).
 The mean of the sample might be different from the

population mean by chance alone.

 The standard deviation of the sample will probably

be different from the population standard deviation.

 We can therefore expect some difference between

the sample statistics (such as the mean and the

standard deviation) and the corresponding
population values, know as parameters. This
47
difference is known as the sampling error.
 Such a difference can be minimized by
developing a sampling distribution for the
sample means.
 In relation to this point, one should note

that the mean of the sampling distribution

and the mean of the population are equal.
 Besides, the variations due to random

fluctuation (or sampling error) decrease as

the sample size increases. However, it is
impossible to avoid the sampling error
completely.
48
 B) SAMPLING BIAS (SYSTEMATIC
ERROR)
 Sampling bias is a non-sampling error which
can be created from errors in the sampling
procedures, and it cannot be reduced or
eliminated by increasing the sample size.
 Such error occurs because of human mistakes

and not chance.

 The possible factors that contribute to the

creation of such bias include:

 inappropriate sampling frame,
 accessibility bias,
 defective measuring device, and
49
 non-response bias (or defects in data collection).
  INAPPROPRIATE SAMPLING

 If the sampling unit is misrepresentation

of the universe, it will result in sampling
bias.
 This could happen when a researcher

gathers data from a sample that was

drawn from some favored locations.
 It occurs when there is a failure of all

units in the Universe to have some

probability of being selected for the
sample (under coverage).
50
  ACCESSIBILITY BIAS
 In a considerable number of research
studies, researchers tend to select
respondents who are the most accessible
to them (easily reached).
 But it should noted that when all

members of the population are not

equally accessible, the researcher must
provide some mechanisms of controlling
so as to ensure the absence of over- and
under-representation of some
respondents. 51
  DEFECTIVE MEASURING
DEVICE
 In some instances, the questions may
not be phrased so they are fully
understandable by respondents.
Consequently, the answers obtained
are not accurate.
 Further more, on any measuring device

(or instrument), most individuals are

likely to be mismeasured to some
degree due to errors in procedures of
observation, interviewing, coding, etc.
52
  NONE-RESPONSE BIAS
 This is an incomplete coverage of sample or inability
to get complete responses from all the individuals
initially included in the sample. This arises due to:
 failure in locating some of the individuals of the
population selected for the sample or
 their refusal to respond.
 the respondents not possessing correct information or
 their giving deliberately biased responses.
 The respondents may intentionally give false information
in response to some sensitive questions.
 For instance, people may not tell the truth about drinking

habits, incomes, or opinions about minorities.

53
 Sometimesthe respondents may give wrong
answers because of ignorance.
 For example, a person may not remember the
exact amount he spent on clothes during the last
years. If asked in a survey, he may give an
inaccurate answer.
 All of these examples result in non sampling
errors.
 Note that non sampling errors can occur both

in a sample survey and in a census, whereas

the sampling errors occur only when a
sample survey is conducted.
 Non-sampling errors can be minimized by

preparing the survey questionnaire and 54

handling the data cautiously

 Samples Size Determination
 The size of the sample is determined by a
number of factors such as:
 the availability of resources (e.g., cost, time,
and personnel),
 the nature of the population (degree of
heterogeneity or homogeneity),
 the degree of accuracy we seek or magnitude of
difference we wish to test
 the confidence levels we wish to use,
 the appropriate size of the population from
which the sample is drawn, and
 the response rate. 55
In any case, the size of the actual
sample must be larger enough:
to allow for reliable analysis of cross-
tabulation;
to provide for desired levels of
accuracy in estimates of proportions,
and
to test for significance of difference
between proportions.
56
57
 Unit Six
Data Collection

BY: Shawel A. (MBA)

58
 CHAPTER CONTENT
• Primary and Secondary Data
• Collection of Primary Data.
• Collection of data through questionnaires
• Collection of data through interview
• Collection of data through observation
• Collection of data through focus group discussion (FGD)
• Collection of Secondary Data

59
 6.1. PRIMARY AND SECONDARY DATA
• The task of data collection begins after a research
problem has been defined and research design/
plan chalked out.
• While deciding about the method of data collection
to be used for the study, the researcher should
keep in mind two types of data viz., primary and
secondary.
• The primary data are those which are collected
afresh and for the first time, and thus happen to be
original in character.
• The secondary data, on the other hand, are those
which have already been collected by someone
else and which have already been passed through
the statistical process. 60
 6.2 COLLECTION OF PRIMARY DATA.
There is a wide variety of primary data gathering
tools available to researchers in the social
sciences; deciding which to use depend on:
 the particular methodology or type of research that
has been selected;
 What is feasible in a given research situation;
 What is likely to yield the most appropriate
information?
Some of the more important data collecting methods for
survey or descriptive research studies are:
 questionnaire,
 interview,
 observation,
 focus group discussions and
 case study methods. 61
 6.2.1. Collection of Data Through Questionnaires
• Quite popular, particularly in case of big enquiries.
• sent (usually by post) to the persons concerned
with a request to answer the questions and return
the questionnaire.
• consists of a number of questions printed or typed
in a definite order on a form or set of forms.
• The respondents have to answer the questions on
their own.
• The method of collecting data by mailing the
questionnaires to respondents is most extensively
employed in various economic and business
surveys.
62
 The merits claimed on behalf of this method are as
follows:

1. There is low cost even when the universe is large

and is widely spread geographically.
2. It is free from the bias of the interviewer; answers
are in respondents’ own words.
3. Respondents have adequate time to give well
thought out answers.
4. Respondents, who are not easily approachable, can
also be reached conveniently.
5. Large samples can be made use of and thus the
results can be made more dependable and reliable.

63
 The main demerits of this system can also be listed:
1. Low rate of return of the duly filled in questionnaires; bias
due to no-response is often indeterminate.
2. It can be used only when respondents are educated and
cooperating.
3. The control over questionnaire may be lost once it is sent.
4. There is inbuilt inflexibility because of the difficulty of
amending the approach once questionnaires have been
dispatched.
5. There is also the possibility of ambiguous replies or omission
of replies altogether to certain questions; interpretation of
omissions is difficult.
6. It is difficult to know whether willing respondents are truly
representative.
7. This method is likely to be the slowest of all.
64
• Before using this method, it is always advisable to
conduct ‘pilot study’ (Pilot Survey) for testing the
questionnaires.
• In a big enquiry the significance of pilot survey is felt
very much.
• Pilot survey is in fact the replica and rehearsal of the
main survey.
• Such a survey, being conducted by experts, brings to
the light the weaknesses (if any) of the
questionnaires and also of the survey techniques.
• From the experience gained in this way, improvement
can be effected.

65
 Main aspects of a questionnaire:
• Quite often questionnaire is considered as the heart
of a survey operation. Hence, it should be very
carefully constructed. If it is not properly set up, then
the survey is bound to fail.
• This fact requires us to study the main aspects of a
questionnaire viz., the:
• general form,
• question sequence and
• question formulation and wording.
• Researcher should note these three main aspects of
a questionnaire:
66
 1. General form:
• It can either be Structured or Unstructured questionnaire.
a) Structured questionnaires:
• are those questionnaires in which there are definite,
concrete and pre-determined questions.
• The questions are presented with exactly the same
wording and in the same order to all respondents.
• Resort is taken to this sort of standardization to ensure
that all respondents reply to the same set of questions.
• The form of the question may be either closed (i.e., of
the type ‘yes’ or ‘no’) or open (i.e., inviting free
response).
• Structured questionnaires may also have fixed
alternative questions in which responses of the
informants are limited to the stated alternatives. 67
 Structured …
• Simple to administer and relatively inexpensive to analyze.
• The provision of alternative replies, at times, helps to
understand the meaning of the question clearly.
• But such questionnaires have limitations too. For instance,
– wide range of data cannot be obtained with structured
questionnaires.
– They are usually considered inappropriate to probe for
attitudes and reasons for certain actions or feelings.
– They are equally not suitable when a problem is being
first explored and working hypotheses sought.
• In such situations, unstructured questionnaires may be
used effectively.
68
 b) Unstructured Questionnaires:
• In an unstructured questionnaire, the
interviewer is provided with a general guide
on the type of information to be obtained,
• But the exact question formulation is largely
his own responsibility and the replies are to be
taken down in the respondent’s own words to
the extent possible; in some situations tape
recorders may be used to achieve this goal.

69
 2. Question sequence:
• The question-sequence must be clear and smoothly-
moving,
• The first few questions are particularly important
• The opening questions should be such as to arouse human
interest. Therefore, avoid,
– questions that put too great a strain on the memory or intellect
of the respondent;
– questions of a personal character;
– questions related to personal wealth, etc.
• Following the opening questions, we should have questions
that are really vital to the research problem and a
connecting thread should run through successive questions.
• Relatively difficult questions must be put towards the end
• Thus, question-sequence should usually go from the
general to the more specific.
70
 3. Question formulation and wording:
• question must be very clear for any sort of misunderstanding
can do irreparable harm to a survey.
• Question should also be impartial in order not to give a
biased picture of the true state of affairs.
• Questions should be constructed with a view to their forming
a logical part of a well thought out tabulation plan.
• In general, all questions should meet the following standards
—
a) should be easily understood;
b) should be simple i.e., should convey only one thought at a time;
c) should be concrete and should conform as much as possible to the
respondent’s way of thinking.
• (For instance, instead of asking. “How many razor blades do you use
annually?” The more realistic question would be to ask, “How many razor
blades did you use last week?”) 71
• Concerning the form of questions, we can talk about
two principal forms, viz.,
– close-end /multiple choice questions and
– open-end question.
a) Close-end question.
• In the close-end questions, the respondent selects
one of the alternative possible answers put to him,
whereas, in the open-end questions he has to supply
the answer in his own words.
• The question with only two possible answers (usually
‘Yes’ or ‘No’) can be taken as a special case of the
multiple choice question, or can be named as a
‘closed question.’

72
 Close-end questions have the following advantages and
disadvantages:
• advantages :
– Easy handling, simple to answer, quick and relatively
inexpensive to analyze.
– They are most amenable to statistical analysis.
– helps to make clear the meaning of the question.
• drawback:
– “Putting answers in people’s mouths”.
– They are not appropriate when the issue under
consideration happens to be a complex one and also
when the interest of the researcher is in the
exploration of a process.
73
 Answer categories in the questionnaire
• In view of Bailey (1982:128), the basic rule for writing
answer categories is to provide all possible answers in
as clear and uncluttered a fashion as possible.
• Nominal scales.
• Inventory method.
• Grid format
• Ordinal/ Likert scales.
• Semantic differential responses.
• Ranked responses.
• Interval scales. (Reading)

74
 b) Open-end question.
• Open-ended questions which are designed to permit a free
response from the respondent rather than one limited to certain
stated alternatives are considered appropriate.
• Advantages and disadvantages:
Permit a free response from the respondent rather than limited to
certain stated alternatives.
• Such questions give the respondent considerable latitude in
phrasing a reply.
• Getting the replies in respondent’s own words.
But;
• from an analytical point of view, open-ended questions are more
difficult to handle, raising problems of interpretation,
comparability and interviewer bias.
75
• In practice, one rarely comes across a case when
one questionnaire relies on one form of
questions alone.
• The various forms complement each other. As
such questions of different forms are included in
one single questionnaire.
– For instance, multiple-choice questions constitute the
basis of a structured questionnaire, particularly in a
mail survey.
– But even there, various open-ended questions are
generally inserted to provide a more complete
picture of the respondent’s feelings and attitudes.
76
• Researcher must pay proper attention to the
wordings of questions since reliable and meaningful
returns depend on it to a large extent.
• Since words are likely to affect responses, they
should be properly chosen.
– Simple words, which are familiar to all respondents,
should be employed. Words with ambiguous meanings
must be avoided.
– Similarly, danger words, catch-words or words with
emotional connotations should be avoided.
– Caution must also be exercised in the use of phrases
which reflect upon the prestige of the respondent.
Question wording, in no case, should bias the answer.
– In fact, question wording and formulation is an art and
can only be learnt by practice. 77
 Essentials of a good questionnaire:
To be successful, Questionnaire should be :
– comparatively short and simple
– proceed in logical sequence moving- from easy to more
difficult questions.
– Technical terms and vague expressions capable of different
interpretations should be avoided
– dichotomous (yes or no answers), multiple choice
(alternative answers listed) or open-ended.
– There should be some control questions in the
questionnaire which indicate the reliability of the
respondent. Eg;…
– Questions affecting the sentiments of respondents should
be avoided.
78
 Essentials…
• Adequate space for answers should be provided.
• There should always be provision for indications of
uncertainty, e.g., “do not know,” “no preference” and so on.
• Brief directions with regard to filling up the questionnaire
should invariably be given in the questionnaire itself.
• The physical appearance of the questionnaire affects the
cooperation.
• The quality of the paper, along with its color, must be good
so that it may attract the attention of recipients.
• A great deal of questionnaires contains a mixture of both.
Eg;…

79
 Cover Letter or Introductory Statement of a
Questionnaire.
• Questionnaire construction consists of writing an
introductory statement or cover letter.
• It justifies the study to the respondent and often
determines whether she/he cooperates or not.
• It should be concise, courteous and businesslike.
• The cover letter is usually written on the
letterhead of the organization conducting or
sponsoring the survey in order to help legitimize
the survey to be conducted to the respondent.

80
 In addition, the introductory statement should:
1. state the purpose of the study and its significance;
2. explain who the data collector is, the basis of its authority, and
why it is conducting the study;
3. tell how and why the respondents were selected;
4. explain why their answers are important;
5. tell how to complete the format and list the person to call if help is
needed to complete the form;
6. provide assurance of confidentiality and anonymity when
appropriate;
7. explain how the data will be used;
8. explain who will have access to the information;
9. Provide mail-back instructions (if necessary); and
10. Present the response efforts as a favor and thank the
respondents for their cooperation.
See example,… 81
 6.2.2. COLLECTION OF DATA THROUGH
INTERVIEW
• The interview method of collecting data
involves presentation of oral-verbal stimuli
and reply in terms of oral-verbal responses.

• This method can be used through personal

interviews and, if possible, through telephone
interviews.

82
 (a) Personal interviews:
It requires a person known as the interviewer asking
questions generally in a face-to-face contact to the other
person or persons.
• This sort of interview may be in the form of direct personal
investigation or it may be indirect oral investigation.
• In the case of direct personal investigation the interviewer
has to collect the information personally from the sources
concerned.
• He has to be on the spot and has to meet people from
whom data have to be collected.
• This method is particularly suitable for intensive
investigations.
83
• But in certain cases it may not be possible or
worthwhile to contact directly the persons concerned
or on account of the extensive scope of enquiry, the
direct personal investigation technique may not be
used.
• In such cases an indirect oral examination can be
conducted under which the interviewer has to cross-
examine other persons who are supposed to have
knowledge about the problem under investigation
and the information obtained is recorded.
– Most of the commissions and committees appointed by
government to carry on investigations make use of this method.
84
• The method of collecting information through
personal interviews is usually carried out in a
structured way. As such we call the interviews
as structured interviews.
• Such interviews involve the use of a set of
predetermined questions and of highly
standardized techniques of recording.
• Thus, the interviewer in a structured interview
follows a rigid procedure laid down, asking
questions in a form and order prescribed.

85
• Unstructured interviews are characterized by:
– a flexibility of approach to questioning.
– do not follow a system of pre-determined questions and
standardized techniques of recording information.
– the interviewer is allowed much greater freedom to ask.
Relatively greater freedom while recording the
responses to include some aspects and exclude others.
– But this sort of flexibility results in lack of comparability
of one interview with another and the analysis of
unstructured responses becomes much more difficult
and time-consuming.

86
 – Unstructured interviews also demand deep
knowledge and greater skill on the part of the
interviewer.
– Unstructured interview, however, happens to be
the central technique of collecting information
in case of exploratory or formulative research
studies.
• But in case of descriptive studies, we quite often use the
technique of structured interview because of its being
more economical, providing a safe basis for generalization
and requiring relatively lesser skill on the part of the
interviewer.

87
 Major advantages of personal interviews
• More information and that too in greater depth
can be obtained.
• Can overcome the resistance,
• yield an almost perfect sample of the general
population.
• greater flexibility .
• Observation method can as well be applied.
• Samples can be controlled more effectively - non-
response generally remains very low.

88
 Major advantages of personal interviews …
• The interviewer can usually control which person (s) will
answer the questions.
• Group discussions may also be held.
• The interviewer may catch the informant off-guard and
thus may secure the most spontaneous reactions.
• The language problem can be avoided.
• Supplementary information about the respondent’s
personal characteristics and environment can collected.

89
 Weaknesses of the interview method.
– It is a very expensive method, especially…
– Possibility of the bias and problem of
supervision and control of interviewer
– Certain types of respondents may not be
easily approachable and to that extent the
data may prove inadequate.
– More time-consuming
– The presence of the interviewer on the
spot may over-stimulate the respondent. 90
 Weaknesses of the interview method. …
– Under the interview method the organization
required for selecting, training and supervising
the field-staff is more complex with formidable
problems.
– Interviewing at times may also introduce
systematic errors.
– Effective interview presupposes proper rapport
with respondents that would facilitate free and
frank responses. This is often a very difficult
requirement.
91
 b) Telephone interviews:
• consists in contacting respondents on telephone
itself.
• It is not a very widely used method,
• The chief merits of such a system are:
– It is more flexible in comparison to mailing
method.
– It is faster than other methods i.e., a quick way of
obtaining information.
– It is cheaper than personal interviewing method.
– Recall is easy; callbacks are simple and economical.
92
 Telephone interviews: …
– There is a higher rate of response than what we have in
mailing method; the non-response is generally very low.
– Replies can be recorded without causing
embarrassment to respondents.
– At times, access can be gained to respondents who
otherwise cannot be contacted for one reason or the
other.
– No field staff is required.
– Representative and wider distribution of sample is
possible.
93
 Some of demerits telephone interview
• Little time is given to respondents for considered answers;
• Surveys are restricted to respondents who have telephone
facilities.
• Extensive geographical coverage may get restricted.
• It is not suitable for intensive surveys where
comprehensive answers are required to various questions.
• Possibility of the bias of the interviewer is relatively more.
• Questions have to be short and to the point; probes are
difficult to handle.

94
 6.2.3. COLLECTION OF DATA THROUGH OBSERVATION
• The most commonly used method especially in studies
relating to behavioral sciences.
• Observation becomes a scientific tool and the method of
data collection for the researcher, when it serves a
formulated research purpose, is systematically planned and
recorded and is subjected to checks and controls on validity
and reliability.
• Under the observation method, the information is sought by
way of investigator’s own direct observation without asking
from the respondent.
– For instance, in a study relating to consumer behavior, the
investigator instead of asking the brand of wrist watch used by
the respondent, may himself look at the watch. 95
 The main advantage
• Subjective bias is eliminated, if observation is done
accurately.
• The information relates to what is currently
happening; it is not complicated by either the past
behavior or future intentions or attitudes.
• Independent of respondents’ willingness to respond.
• Particularly suitable in studies which deal with
subjects (i.e., respondents) who are not capable of
giving verbal reports of their feelings for one reason
or the other.

96
 Limitations of observation method

• it is an expensive method.
• the information provided by this method is
very limited.
• sometimes unforeseen factors may interfere
with the observational task.
• At times, the fact that some people are rarely
accessible to direct observation

97
 6.2.4. COLLECTION OF DATA THROUGH FOCUS GROUP
DISCUSSION (FGD)
• With origins in sociology, widely applicable in
business research.
• A FGD is a discussion made by a panel of 8 to 12
respondents led by a trained moderator. …
• The output of the session is a list of ideas and
behavioral observations with recommendations of
the moderator.
• Particularly, in exploratory research, the qualitative data
that focus groups produce may be used for enriching all
levels of research questions and hypotheses and
comparing the effectiveness of design options. 98
 Qualities of a moderator:
• The moderator should be equipped with sufficient skill
so that… he/she can maintain a high degree of
interaction among group members.
• It is only with interaction the focus group
discussion can:
– Provide the desired spontaneity of response by
participants,
– Produce the degree of emotional involvement
essential to produce "depth" level responses, and
– Produce the kind and degree of rapport which
facilitates a "give and take " exchange of attitudinal
and behavioral information. 99
 6.3. COLLECTION OF SECONDARY DATA
• Secondary data means data that are already
available i.e., they refer to the data which
have already been collected and analyzed by
someone else.
• When the researcher utilizes secondary data,
then he has to look into various sources from
where he can obtain them.
• Secondary data may either be published data
or unpublished data.

100
• Usually published data are available in:
a) various publications of the central, state are local
governments;
b) various publications of foreign governments or of
international bodies and their subsidiary organizations;
c) technical and trade journals;
d) books, magazines and newspapers;
e) reports and publications of various associations
connected with business and industry, banks, stock
exchanges, etc.;
f) reports prepared by research scholars, universities,
economists, etc. in different fields; and
g) public records and statistics, historical documents, and
other sources of published information. 101
• The sources of unpublished data are many; they may be
found in diaries, letters, unpublished biographies and
autobiographies and also may be available with
scholars and research workers, trade associations,
labor bureaus and other public/ private, individuals
and organizations.
• Researcher must be very careful in using secondary
data. - secondary data may be unsuitable or may be
inadequate in the context of the problem
• In this connection Dr. A.L. Bowley: “ it is never safe to
take published statistics at their face value without
knowing their meaning and limitations”

102
Before using secondary data, the researcher must see
that they possess following characteristics:

– The already available data should be used by

the researcher only when he finds them
reliable, suitable and adequate.
– But he should not blindly discard the use of
such data if they are readily available from
authentic sources and are also suitable and
adequate for in that case it will not be
economical to spend time and energy in field
surveys for collecting information.
103
The End !
104