Module 5 - Research Design
Module 5 - Research Design
Module 5 - Research Design
Age
Extraneous Variable
POINT TO REMEMBER
Avoid Bias/ Increase Reliability
The difference between research designs in respect of the above two types of research studies
(i.e. exploratory and Descriptive/Diagnostic) can be conveniently summarized as under:
3. Research design in case of hypothesis-testing research studies:
• Hypothesis-testing research studies (generally known as experimental studies) are those
where the researcher tests the hypotheses of relationships between variables.
• Such studies require procedures that will reduce bias and increase reliability,
• Experiments meet this requirement.
• Hence, when we talk of research design in such studies, we often mean the design of
experiments.
• Professor R.A. Fisher’s name is associated with experimental designs, who worked at
Rothamsted Experimental Station (Centre for Agricultural Research in England).
• Therefore, his study is focused on agricultural research, and he designed experiments for
his study
• Professor Fisher found that by dividing agricultural fields or plots into different blocks
and then by
conducting experiments in each of these blocks, whatever information is collected and
inferences drawn from them, happens to be more reliable.
• This fact inspired him to develop certain experimental designs for testing hypotheses
concerning scientific investigations.
• Today, the experimental designs are being used in researches relating to phenomena of
several disciplines.
• Since experimental designs originated in the context of agricultural operations, we still
use, though in a technical sense, several terms of agriculture (such as treatment, yield,
plot, block etc.) in experimental designs.
Basic Principles of Experimental Designs
• Professor Fisher has enumerated three principles of experimental designs:
(1) The Principle of Replication;
(2) The Principle of Randomization; and
(3) The Principle of Local Control.
• Drawback of this approach is “Extraneous variation” may be there, and not accounted for
• Example – Demonstrate Hook’s Law in Lab – But if I want to verify elasticity of some material
with the same equipment, what will be extraneous variables?
2. After-only with control design:
• In this design two groups or areas (test area and control area) are selected and the treatment is
introduced into the test area only.
• The dependent variable is then measured in both the areas at the same time.
• Treatment impact is assessed by subtracting the value of the dependent variable in the control
area from its value in the test area.
• This can be exhibited in the following form:
• The basic assumption in such a design is that the two areas are identical with respect to their
behavior towards the phenomenon considered.
• If this assumption is not true, there is the possibility of extraneous variation entering into the
treatment effect.
• However, data can be collected in such a design without the introduction of problems with the
passage of time.
3. Before and after with Control Design
• In this design two areas are selected, and the dependent variable is measured in both the areas for
an identical time-period before the treatment.
• The treatment is then introduced into the test area only, and the dependent variable is measured
in both for an identical time-period after the introduction of the treatment.
• The treatment effect is determined by subtracting the change in the dependent variable in the
control area from the change in the dependent variable in test area.
• This design is superior to the above two designs for the simple reason that it avoids extraneous
variation resulting both from the passage of time and from non-comparability of the test and
control areas.
• But at times, due to lack of historical data, time or a comparable control area, we should prefer to
select one of the first two informal designs stated above.
Formal Experimental Designs:
Completely Randomized Design (C.R. Design)
• It is the simplest possible design and its procedure of analysis is also easy
• The essential characteristic of the design is that subjects are randomly assigned to
experimental treatments
• For instance, if we have 10 subjects and if we wish to test 5 under treatment A and 5
under treatment B, the randomization process gives every possible group of 5 subjects
selected from a set of l0 an equal opportunity of being assigned to treatment A and
treatment B
Group 1
Treatment A
5 Subjects
Experimental Unit Random
(Subjects) 10 Assignment Compare
Results
Group 2
Treatment B
5 subjects
Example:
A researcher wants to conduct an experiment to determine which environment is best suited
for self study:
a) Library
b) One’s own room
c) Outside (Lawn/Public Park)
Assume that 30 student volunteers have agreed to participate in the research
Solution
a) There are 3 groups
b) There are 30 students – 3 groups, to receive 3 treatments (one each)
c) Each group will have 10 students randomly selected.
d) One group will be asked to study in library, second in his own room and the third in Park.
e) Results will be evaluated and compared.
Let, the researcher, thinks that he has not considered the effect of gender on the above analysis –
So he makes the groups of female and male …. As in the next slide
Example:
You want to test quality of petrol from 3 petrol pumps. Design an experiment, based on
random sampling technique – from which petrol pump, car does the maximum km per liter?
Randomized block design (R.B. design)
• Assume that in previous example, researcher discover that “Gender has an extraneous
effect on the results” – so decides to take this aspect into account.
• Randomized block design (R.B. design), an improvement over the C.R. design addresses
this issue.
• In the R.B. design, subjects are first divided into groups, known as blocks, such that
within each group the subjects are relatively homogeneous in respect to some selected
variable
• In this method, we first assign people in block based on characteristic that is expected to
influence the response to the treatment
• In this example, gender is “block”, i.e. we divide our research into two block, i.e. male
and female.
• Now find number of female and male students, out of volunteers,: Say 18 female and 12
male students have volunteered in this study.
• So, we separate our experimental units into two “blocks” based on gender
• Each block will be further divided into 3 groups, subjected to one treatment.
• It can be seen that groups will contain 6 female and 4 male in each group
• Results are then compared.
• It is shown in next slide.
Treatment 1 - Library
Group 1 (6)
30 Students
Group 1 (4) Treatment 1 - Library