2. INTRODUCTION
Experimental is most scientifically sophisticated research method.
It is defined as ‘observation under controlled conditions’.
Experimental research design are concerned with examination of the effect of
independent variable on the dependent variable, where the independent variable is
manipulated through treatment or intervention & the effect of those interventions
is observed on the dependant variable.
3. ELEMENTS OF EXPERIMENTAL RESEARCH
Random assignment of subjects to groups
Precisely defined independent variable
Manipulation of independent variable
Having a comparison group
Clearly identified sampling criteria
Carefully measured dependent variables
Controlled environment for conducting study
4. SYMBOLIC PRESENTATION
R = Random assignment of the subjects to groups
O = Observation or measurement of dependent variable
X = Experimental treatment or intervention
7. CONCEPT
True experimental research designs are those where researchers have
complete control over the extraneous variables & can confidently predict
confidently that the observed effect on the dependable variable is only
due to the manipulation of the independent variable.
9. MANIPULATION
Manipulation refers to conscious control of the independent variable by the
researcher through treatment or intervention(s) to observe its effect on the
dependent variable.
Example: ‘A study evaluated the effectiveness of gentle back massage on
improving quality of sleep among depressive patients.’
Receiving gentle back massage is the independent variable in this example. This
could be manipulated by giving back massage to some patients and withholding it
for others, later patients quality of sleep (dependent variable) is compared among
the two groups to infer whether differences in receiving the intervention resulted
in differences in quality of sleep.
10. CONTROL
Control means use of control group and controlling the effects of extraneous variables
on the dependent variable.
The subject in the control & experimental groups are similar in number &
characteristics, but the subject in the control group receive no experimental treatment
or any intervention at all.
controls ate classed as
Negative control
Clear control
Positive control
11. RANDOMIZATION
Randomization means introduction of chance into the selection or assignment or
subjects to treatments.
Randomization can occur at two levels
Random selection
Random assignment:
Methods
Flip of coin
Lottery method
Random table
Computer-assisted random
12. TYPES OF TRUE EXPERIMENTAL DESIGN
True
experimental
design
Basic post test
only design
Basic pre-test
post-test
design
Solomon four
group designs
Factorial
design
Crossover
design
13. BASIC POST TEST ONLY DESIGN
In this design, dependent variable is measured only once after the experimental
treatment has been administered.
Schematic diagram: RE X O1
RC O1
Example: A study to eventuate the effectiveness of antenatal exercise on labor
Outcome among antenatal mothers.
14. BASIC PRE-TEST POST-TEST DESIGN
This is a classic experimental design wherein the dependent variable is measured at
two points in time, i.e. before and after the experimental intervention.
Schematic diagram: RE O1 X O2
RC O1 O2
Example: The efficacy of body-mind-spirit intervention on well-being and quality of
life among depressive patients from the pretest.
15. SOLOMON FOUR GROUP DESIGNS
This design has four groups two experimental and two controls. While one
experimental and one control group are administered pretest, the other two groups are
not. Post test is conducted for all the groups.
Schematic diagram: RE1 O1 X O2
RC1 O1 O2
RE2 X O1
RC2 O1
16. CONT..
Example: Nursing students completed a questionnaire measuring their knowledge
scores on drug calculation as a pretest. Later, the students might look up for answers
to some unknown questions. This might result in scoring better on the posttest
compared to scoring without taking the pretest. This example suggests that pretest
sensitization had an influence on posttest scores. To avoid this sensitization, Solomon
four-group design is used.
17. FACTORIAL DESIGN
Independent variables are sometimes called factors. When the researcher uses
multiple independent variables in a study, it is called factorial design. In this design,
two or more independent variables are manipulated by the researcher simultaneously
to observe their effects on the dependent variable.
Schematic diagram: RA O1 X1 + X2 O2
RB O1 X1 O2
RC O1 X2 O2
RD O1 O2
18. CONT..
Example: In a study to evaluate the effectiveness or relaxation and distraction on
reduction or pain among cancer patients, a 2 x 2 factorial design with four cells (A, B,
C, and D) are used. Each cell contains equal number of subjects. Cell A subjects
receive distraction and relaxation intervention, cell B subjects receive only distraction
intervention, cell C subjects receive only relaxation intervention, cell D subjects
receive no intervention and serve as a control group. Cell A subjects allow the
researcher to examine the interaction between two independent variables, relaxation
and distraction.
19. CROSSOVER DESIGN
In this design subjects are exposed to more than one treatment where subjects are
randomly assigned to different orders of treatment. It is also known as repeat
measures design.
Schematic diagram: RE1 O1 X1 O2 X2 O3
RE2 O1 X2 O2 X1 O3
Example: A study to compare the effectiveness of massage and music therapy on the
development of premature infants. In this study, some infants are randomly assigned
to receive massage therapy first and music therapy later. However, the other infants
receive music therapy first and massage therapy later.
20. RANDOMIZED CONTROLLED TRIALS
Well-designed Randomized controlled trials (RCTs) arc considered the gold standard
for measuring the Intervention effect.
This method is used in various fields such as medicine, psychology, education, and
administration.
Randomized controlled trials are quantitative, comparative, controlled experiments
wherein the investigator evaluates the effect of intervention by administering it to
subjects who have been randomly assigned to either of the experimental or control
groups.
21. CONT..
Steps:
Subjects are randomly assigned to intervention or control groups.
Subjects in one group receive the treatment being tested; the other receives an
alternate treatment or placebo or no treatment.
Both the groups are followed up and outcomes measured at specific intervals.
These outcome measures are statistically compared to assess the difference in
response between the groups so as to study the effect of experimental treatment.
22. CONT..
Advantages:
The most powerful way to find out cause- and-effect relationship
Blinding is possible
Completely removes effect of extraneous variables
Strict protocols are followed
Disadvantages:
Recruitment of sample may be difficult
Costly and time consuming
Hawthorne effect
23. ADVANTAGES AND DISADVANTAGES OF TRUE
EXPERIMENTAL DESIGN
Advantages:
It is most scientific in nature
True experiments because of their rigor precision, and control properties are
Considered the most powerful methods for testing hypothesis of cause-and effect
relationship between variables
Randomized controlled trial is placed at the highest level on the evidence-bag practice
pyramid
24. ADVANTAGES AND DISADVANTAGES OF TRUE
EXPERIMENTAL DESIGN
Disadvantages:
Sometimes criticized for their artifiality
Due to ethical reason manipulation can not be done in human studies.
Pretest effect
26. CONCEPT
Quasi experimental designs facilitate the experimentation of causality in
situations in which complete control is not possible. In these designs, one
of the components of true experiment design i.e. either the random
assignment of subjects to groups or control groups for comparison are
typically lacking.
28. TYPES OF QUASI EXPERIMENTAL DESIGN
Quasi
experimental
design
Pre-test post-
test with
control group
design
Only control
post test
design
One group
pre-test post
test design
One group
post test only
design
Time series
design
Single-group
interrupted time
series design
Time series with
control group
design
29. PRE-TEST POST-TEST WITH CONTROL GROUP DESIGN
This design is similar to pre-post control group Design except that the participants are
not randomly (NR) assigned to groups.
Schematic diagram: E O1 X O2
C O1 O2
Example: In a study to evaluate the effectiveness of therapeutic environment on
conflict and containment rates among schizophrenia patients, the experimental group
and comparison group subjects were admitted to different psychiatric wards. As the
ward environment is manipulated for the study purposes the researcher preferred
different wards for experimental and control subjects to avoid contamination of
treatment conditions.
30. ONLY CONTROL POST TEST DESIGN
In this design, the dependent variable is measured only once after the experimental
treatment has been introduced.
Schematic diagram: E X O1
C O1
Example: A study to evaluate the efficacy of distraction in reducing pain perception
among children in this study, the researcher provides distraction to the experimental
group children while no distraction is provided to the control group children during
the painful procedure. He then examines the differences in amount of pain during the
procedure between the subjects in two groups. In this study, it is not possible to
pretest the amount of pain before the procedure.
31. ONE GROUP PRE-TEST POST -TEST DESIGN
This design is used when only one group is available for study. Dependent variable is
assessed (pre-test) before implementation of the intervention to the subjects followed
by post-test observation.
Schematic diagram: O1 X O2
Example: In a study on sexual behavior in teens, behavior is measured baseline
(pretested), a nurse-based educational intervention is administered and subsequent
behavior is measured again (posttest).
32. ONE GROUP POST TEST ONLY DESIGN
In this research design, a single experimental group is exposed to a treatment &
observations are made after that treatment.
Schematic diagram: X O1
Example: In a study to evaluate the effectiveness of group therapy on well-being of
diabetic patients, the researcher chose the patients with diabetes in experimental
group from selected hospitals.
33. SINGLE-GROUP INTERRUPTED TIME SERIES DESIGN
In this design researcher collects data multiple times at pretest level. Later, subjects
are administered experimental treatment which is followed by collection of data at
multiple time points.
Schematic diagram: O1 O2 O3 X O4 O5 O6
Examples: A researcher may evaluate pain levels of arthritis patients. After assessing
pain levels for 3 weeks at weekly intervals, the subjects were provided physiotherapy
to reduce pain. The pain levels are again evaluated for the next 2 weeks.
34. TIME SERIES WITH CONTROL GROUP DESIGN
Here, the researcher collects data multiple times at pretest level after which subjects
are administered experimental treatment followed by collection of data at multiple
time points.
Schematic diagram: E O1 O2 O3 X O4 O5 O6
C O1 O2 O3 O4 O5 O6
Examples: A research may evaluate anxiety levels of school students studying at
class10. After assessing for anxiety levels for 3 weeks at weekly intervals (both the
groups), the Subjects in experiment group are provided Cognitive behavioral therapy
to reduce anxiety. The anxiety levels are again evaluated for the next 3 weeks.
35. ADVANTAGES AND DISADVANTAGES OF QUASI
EXPERIMENTAL DESIGN
Advantages:
Feasible, practical and generalizable.
More adaptable to the real world practice setting than true experimental designs.
For some hypotheses these designs may be the only way to evaluate the affect of the
Independent variable of interest.
Introduce some research control when full experimental rigor is not possible.
36. ADVANTAGES AND DISADVANTAGES OF QUASI
EXPERIMENTAL DESIGN
Disadvantages:
There is no control over extraneous variables influencing the dependent variable
Lack of randomization or absence of control group makes the results of the study less
reliable and weak for establishing the cause and effect relationship between
independent and dependent variables.
37. CONCLUSION
Experimental research designs are often considered to be the standard in research
designs. In this research design, one or more subjects or dependent variables are
randomly assigned to different treatments and the results are observed to conclude. One
of the uniqueness of experimental research is in its ability to control the effect of
extraneous variables. Experimental research is suitable for research whose goal is to
examine cause-effect relationships, e.g. explanatory research. It can be conducted in the
laboratory or field settings, depending on the aim of the research that is being carried
out.