4/12/2020

Research Design
Azhan Abdul Aziz

Introduction
COMMUNICATE
FINDINGS
ANALYZE DATA •Discuss and
report the results.
•Analyzing
COLLECT DATA according to the
research
•Gather data after questions.
PREPARE determining the
RESEARCH sample and
INSTRUMENT setting
DETERMINE •How will you
RESEARCH collect the data?
DEFINE AIM & DESIGN
OBJECTVES
•What decision • What research
you are trying to method will you
find out? employ?

1
 4/12/2020

Definition
 A Research design is a plan, structure and strategy of
investigation, so conceived as to obtain answer to research
questions or problems. The plan is the complete program of the
research. It includes an outline of what the investigator will do
from writing the hypothesis and their operational implications to
the final analysis of data. (Kerlinger, 1986)

 A traditional research design is the blue-print or detailed plan for

how a research study is to be completed – operationalizing
variables so they can be measured, selecting a sample of
interest to study, collecting data to be used as a basis for testing
hypothesis and analysing the results. (Thyer, 1993)

Definition
 “Research design is the arrangement of conditions for
collection and analysis of data in the manner that aims to
combine relevance of research purpose with economy in
process” (Selltiz et al, 1976)

 “Summarizes the essential of research design as an activity

and time based plan; always based on the research question;
guide the selection of sources and types of information; a
framework for specifying the relationship among the study
variables and outlines the procedures for every research
activity. ” (Cooper and Schindler, 2003)

2
 4/12/2020

Definition
 Research design : a framework of methods and techniques
chosen by a researcher to combine various components of
research in a reasonably logical manner so that the research
problem is efficiently handled. It provides insights about “how” to
conduct research using a particular methodology.

 Research design is devised to assess a list of research

questions. Research problem will determine the research
design, and not vice-versa.

 Research design explains the type of research (e.g.

experimental, survey, correlational, semi-experimental) and also
its sub-type (e.g. experimental design, descriptive case-study).

Definition
Research Design Research Method
Overall structure of the research The procedures that will be used to
collect and analyze data

Focuses on what is planned and

what kind of results are expected Focuses on what type of methods
from the research are more suitable to collect and
analyze the evidence needed

Based on the research question or

problem Depend on the research design

3
 4/12/2020

Implications
 Research design concerns 3 main sections :
1. data collection
2. measurement
3. analysis

 Research design determines the:

 variables
 designated tools to gather information
 how the data will be collected
 how the data will be analyzed
 other factors related to research techniques

 Good research design strives to minimize bias in data and increase

trust on the collected and analyzed research information.

Essential Elements

Techniques to be Method applied for

Accurate purpose Type of research
implemented for analyzing
statement methodology
collecting data collected data

Probable
Settings for Measurement of
objections for Timeline
research study analysis
research

4
 4/12/2020

Research Design Characteristics

 4 key characteristics of research design:

Research Design Characteristics

 Neutral
 The results projected in research design should be free from bias
and neutral. Understand opinions about the final evaluated
scores and conclusion from multiple individuals and consider
those who agree with the derived results.

5
 4/12/2020

Research Design Characteristics

 Reliable:
 If a research is conducted on a regular basis, the researcher
involved expects similar results to be calculated every time.
Research design should indicate how the research questions can
be formed to ensure the standard of obtained results and this can
happen only when the research design is reliable.

Research Design Characteristics

 Valid:
 There are multiple measuring tools available for research design
but valid measuring tools are those which help a researcher in
gauging results according to the objective of research and
nothing else. The questionnaire developed from this research
design will be then valid.

6
 4/12/2020

Research Design Characteristics

 Generalizability:
 The outcome of research design should be applicable to a
population and not just a restricted sample. Generalization is one
of the key characteristics of research design.

Types of research design

 2 broad classifications of Research design are:

Qualitative Quantitative
Research Research
Design: Design:
Researchers rely on
Quantitative research is
qualitative research design
implemented in cases where
where they expect to
it is important for a
conclude “why” a particular
researcher to have statistical
theory exists along with
conclusions to collect
“what” respondents have to
actionable insights.
say about it.

7
 4/12/2020

Types of research design

 Research design may be further classified as:
1. Descriptive Research Design
2. Experimental Research Design
3. Correlational Research Design
4. Diagnostic Research Design
5. Explanatory Research Design

Types of research design

 Descriptive Research Design
 In a descriptive research design, a researcher is interested solely
in describing the situation or case under his/her research study. It
is a theory-based research design which is created by gathering,
analyzing and presenting collected data. By implementing an in-
depth research design such as this, a researcher can provide
insights into the why and how of a phenomenon.

8
 4/12/2020

Types of research design

 Experimental Research Design:
 Experimental research design is used to establish a relationship
between the cause and effect of a situation. It is a causal
research design where the effect caused by the independent
variable on the dependent variable is observed.
 The independent variables are manipulated to monitor the
change it has on the dependent variable.
 It is a highly practical research design method as it contributes
towards solving a problem at hand. It is often used in social
sciences to observe human behavior by analyzing two groups –
affect of one group on the other.

Types of research design

 Correlational Research Design:
 Correlational research is a research design technique which helps
researchers to establish a relationship between two closely
connected variables. Two different groups are required to conduct
this research design method. There may be no assumption while
evaluating a relationship between two different variables and
statistical analysis techniques are used to calculate the relationship
between them.
 Correlation between two variables is concluded using a correlation
coefficient, whose value ranges between -1 and +1. If the correlation
coefficient is towards +1, it indicates a positive relationship between
the variables and -1 indicates a negative relationship between the
two variables.

9
 4/12/2020

Types of research design

 Diagnostic Research Design:
 In the diagnostic research design, a researcher is inclined
towards evaluating the root cause of a phenomenon. Elements
that contribute towards a troublesome situation are evaluated in
this research design method.
 There are three parts of diagnostic research design:
1. Inception of the issue
2. Diagnosis of the issue
3. Solution for the issue

Types of research design

 Explanatory Research Design:
 This research design offers explanation about unexplored
aspects of a subject through gathering and presentation of details
about what, how and why that relate to the research questions.
 In this research design, the researcher’s ideas and thoughts are
key as it is primarily dependent on their personal inclination about
a particular topic.

10
 4/12/2020

Types of research design

One Cross sectional study

Number of Contacts Two Before & after study

Three Longitudinal study

Retrospective

Reference Period Prospective

Retrospective-prospective

True Experimental
Experimental
Nature of Investigation Qausi-experimental
Non-experimental

Types of research design

NON-EXPERIMENTAL QUASI-EXPERIMENTAL TRUE EXPERIMENTAL

At least one IV is not manipulated

IVs are not manipulated All IVs are manipulated
(e.g. subject variable)

Participants not assigned to Participants not assigned to all IV

conditions conditions Participants assigned to conditions

No group comparison Comparison group Explicit comparison group

Weak causal inferences Moderate causal inferences Strong causal inferences

11
 4/12/2020

Types of research design

TRUE EXPERIMENT QUASI-EXPERIMENT

Emphasis Emphasis
•Assess cause & effect •Describe “real”/natural event
•Test clear, a priori hypothesis •Clear or exploratory hypothesis

Participant Participant
•Control group •Existing group
•Randomly assigned •Non-random assignment
•Double blind •Participants not blind

Level of control Level of control

•Manipulate independent variable •Unable to manipulate independent
•Control of procedure & measure variable
•Partial control of procedure & measure

Types of research design

 ADVANTAGES OF QUASI-EXPERIMENTAL DESIGN
 More practical and feasible to conduct in absence of a large
sample, randomization and/or availability of control groups
 More suitable for real-world natural setting than true experimental
research design
 Allows researchers to evaluate the impact of quasi independent
variables under naturally occurring conditions
 In some cases hypotheses may be answered through this design

12
 4/12/2020

Characteristics of Good Research

(Cooper & Schindler, 2003).

Characteristics of Good Research

Purpose clearly defined.

• The problem and purpose of the research must be clearly defined [unambiguous
terms]
• The statement of the problem should include scope, limitations, and definition of all
significant words and terms.
• Otherwise, this may show researcher’s has insufficient understanding of the
problem.

Research process detailed.

• The research procedures should be described in sufficient detail to permit

duplication [including steps & procedures to acquire and gather data]
• Except when secrecy is imposed, research reports should reveal the sources of
data and the means by which they were obtained.
• Otherwise, this will make it difficult to estimate the validity and reliability of the data

13
 4/12/2020

Characteristics of Good Research

Research design thoroughly planned.
• The choice and procedures of the research design should be clearly described and
carefully planned to yield objective results [e.g. survey of opinions or recollections ought
not to be used when more reliable evidence is available from documents or direct
observation)
• Literature searches should be as thorough and complete as possible.
• Experiments should have satisfactory controls, reducing threats to internal validity and
enhancing the probability of external validity (generalizability).
• Efforts should be made to minimize personal bias in selecting and recording data.

High ethical standards applied.

• Research should safeguard against causing mental or physical harm to participants.
• Incases when there is a need to balance the rights of the subjects against the scientific
dictates of the method, welfare of the participants/organizations should be guarded.
• The research design must carefully consider the possible adverse effects such as
physical or psychological harm, exploitation, invasion of privacy, and/or loss of dignity.

Characteristics of Good Research

Limitations frankly revealed.
• The researcher should frankly report flaws in procedural design and estimate their effect
on findings
• There are very few perfect research designs. Some of the imperfections may have little
effect on the validity and reliability of the data; others may invalidate them entirely.
• Stake holders tend to question the value of research without limitation reports

Adequate analysis for stake holder’s needs.

• The methods of analysis should be appropriate and extensive enough to reveal its
significance.
• The validity and reliability of data should be checked carefully.
• The data should be classified in ways that assist the researcher in reaching pertinent
conclusions and clearly reveal the findings that will lead to a justified conclusions.
• When statistical methods are used, appropriate descriptive and inferential techniques
should be chosen, the probability of error should be estimated, and the criteria of
statistical significance applied.

14
 4/12/2020

Characteristics of Good Research

Findings presented unambiguously.
• Report must display language that is clear and precise; assertions that are carefully
drawn and hedged with appropriate reservations; and an apparent effort to achieve
maximum objectivity.
• Avoid generalizations that outrun the statistical findings, exaggerations and unnecessary
verbiage.
• Presentation of data should be comprehensive, reasonably interpreted, easily
understood, and organized so that the reader can effortlessly locate critical findings.

Conclusions justified.
• Conclusions should be limited to those for which the data provide an adequate basis.
• Avoid including personal experiences and interpretations.
• Do not make generalization from a study of a limited population.
• Always specify the conditions under which conclusions seem to be valid.

References
 Cooper, D.R. & Schindler, P.S. (2003). Business research
methods. Florida Atlantic University, Pamela S. Schindler,
Wittenberg University. 12th. edition.
 Creswell, J.W. (2003). Research Design: Qualitative,
Quantitative, and Mixed Methods Aproaches, 2nd Edition.
Thousand Oaks, CA: Sage Publication.
 Kerlinger, F.N. (1986). Foundations of Behavioural Research.
New York: Subject Publications.
 Thyer, BA (1993).Single-system research designs. Social work
research and evaluation (4).
 Selltiz, Wrightsman and Cook (1976). Research Methods in
Social Relations. Publisher: Holt Rinehart and Winston

15
 4/12/2020

Thank You
Azhan Abdul Aziz

16