Meaning, Purpose
& Criteria Of
RESEARCH DESIGN
Presenting By,
Agin Tom
1st MSc Clinical Psycholo
Meaning of Research Design
• Research design is a detailed plan for an investigation.
• It is the blueprint of the detailed procedures of the
testing of hypotheses and analysis of data.
• Research design ensures relevant data collection for
objective analysis.
• It helps researcher in testing the hypothesis by
reaching valid and objective conclusions about
relationships between independent and dependent
variables.
• Research design selection is based on investigation
purpose, types of variables, and research conditions,
not on researcher preferences.
Purpose of Research Design
The purpose of any research design is to efficiently gather
relevant information to the problems under investigation at a
minimizing costs. It serves two main functions:
first, to objectively and economically answer research
questions and hypotheses, guiding data collection, variable
treatment, manipulation methods, statistical analyses, and
providing potential answers.
Second, it acts as a control mechanism, helping to manage
experimental, extraneous, and error variances, ensuring the
validity of the research outcomes.
1. Experimental Variance
• Experimental variance occurs when the dependent variable is
affected by changes in the independent variables manipulated by
the experimenter.
• The goal is to maximize this variance to obtain valid and objective
data. To achieve this, the experimenter designs experiments to
make the experimental conditions as distinct as possible.
For instance, in a study on how reward affects learning rate, subjects
are placed into high, medium, and low reward conditions. A higher
variance is achieved when the differences between conditions are
pronounced. Conversely, if conditions are similar, the variance is
minimized. Therefore, experimenters strive to maximize
2. Extraneous Variance or Control
Variance
• An extraneous variable is any variable not being investigated that
has the potential to affect the outcome of a research study. In
other words, it is any factor not considered an independent
variable that can affect the dependent variables or controlled
conditions.
• An experimenter always tries to control the relevant variables and
thus, also wants to eliminate the variances produced by these
variables.
For elimination of extraneous variance, it is essential that the
extraneous variables be properly controlled. If left uncontrolled,
extraneous variables can lead to inaccurate conclusions about the
relationship between independent and dependent variables.
Error Variance
The role of research design includes minimizing error variance, which
arises from uncontrollable factors affecting measurements.
These factors include individual differences among subjects such as to
their attitude, motivation, need ability etc., and they may be related to
what is commonly called measurement errors like differences in trials,
experimental conditions, emotional state of subject etc.
• Error variance is self-compensating, because sometimes the variability
is positive and negative.
Since error variance is both positive and negative, it tends to cancel
out in repeated measurements, then the mean of error variance will be
zero.
• It is unpredictable due to random errors.
Minimizing error variance enhances the reliability of measures,
strengthens external validity, and allows systematic variance to show
significance.
Controlling experimental conditions reduces error variance.
A good research design aims to provide clear results by avoiding
confounding, where multiple variables change simultaneously,
obscuring cause-effect relationships.
Criteria of Research Design
Research design is data discipline. There are various
types of research designs. Some are weak designs while
some are strong.
Behavioural researchers have been able to formulate
certain criteria on the basis of which a weak research
design can readily be distinguished from a strong one.
These criteria have proved very useful in guiding the
researchers in the correct direction.
1. Capability to answer research questions adequately
2. Control of variables
3. Generalizability
[Link] to Answer Research Questions
Adequately
A good research design is the design that answer research
questions adequately.
Researchers sometimes choose design that are not suitable
for their specific questions, resulting in weak research designs
that fail to adequately test the hypothesis. Students often
match subjects by sex, age, and intelligence, assuming this
will improve experimental and control groups.
• If the factors are unrelated to the dependent variable,
such matching is irrelevant and weakens the design.
• Similarly, if a study requires 4 groups (e.g., 3
experimental and one control) but only uses a two-
group randomized design, the research questions will
not be adequately answered. For testing interaction
hypotheses, a factorial design is appropriate, while a
two-group randomized design is not.
2. Control of variables
A good research design should control the effects of extraneous
variables, which can influence dependent variables similarly
to independent variables. If not controlled, these are called
extraneous variables. A design that fails to control them is
weak and should be avoided.
Randomization is one of the best techniques to control
extraneous variables.
It involves three phases: random selection of
subjects, random assignment of subjects to control and
experimental groups, and random assignment of
treatments to groups.
If random selection is not possible, random
assignment to groups or treatment is used instead.
Effective randomization enhances the internal validity
of the research, making it the best design.
3. Generalizability
The third criteria of research design,
Generalizability, refers to how well the results of
a study can apply to subjects, groups, or
conditions beyond the sample used.
If the design allows for broader application of
results, its considering strong.
This applies differently to basic and applied
research: basic research focuses on
understanding relationships among variables,
while applied research emphasizes applying
Reference
Singh, A. K. (2017). Tests, measurements and
research methods in behavioural sciences. New
Delhi, India: Bharati Bhawan Publishers &
Distributors.