3. *KEY IDEAS
What is an experiment?
Key characteristics of experimental design
Threat or Validity
Treatment Conditions
Steps in conducting experimental research
Types of experimental design
When do we use an Experimental research?
Limitations
4. *What IS AN EXPERIMENT?
Research methods in which
Conditions are controlled so that one or more
independent variables can be manipulated to
test a hypothesis about a dependent variable .
Allows
Evaluation of causal relationships among
variables while other variables are eliminated or
controlled.
5. *KEY
CHARACTERISTICS
Dependent variable
variables that is expected to be dependent on the
manipulation of the independent variable.
Independent variable
Any variable that can be manipulated or altered
independently of any other variable.
Experimental treatments
Alternative manipulations of the independent variable
being investigated.
6. *KEY
CHARACTERISTICS
*Participants selected and assigned to groups
control- group of subjects exposed to the control condition
- Not exposed to the experimental treatment
Experimental- group of subjects exposed to the experimental
treatment
An intervention is applied to one or more groups
Outcomes are measured at the end of the experiment.
7. *THREATS OF VALIDITY
*Procedures are designed that address
potential threats to validity
Internal
External
Construct
Statistical Conclusion
8. *Threats to Internal
Validity
This category addresses the threats related to
participants in the study and their experiences..
*History
*Maturation
*Regression
*Selection
*Mortality
*Interactions with selection
9. *Threats to Internal
Validity
The next category addresses the threats related to treatment
*Diffusion of treatments
*Compensatory equalization
*Compensation rivalry
*Resentful demoralization
The last category addresses the threats that typically occur
during an experiment and related to the procedures of the
study..
*Testing
*Instrumentation
10. *Threats to External Validity
*Interaction of selection and
treatment
*Interaction of setting and treatment
*Interaction of history and treatment
11. *Threats to Statistical
Conclusion Validity
*Low statistical power due to low sample size
*Violation of assumptions of statistical tests
*Use of unreliable measures
12. *Threats to Construct
Validity
*Lack of good operational definitions
*Apprehensiveness by participants
*Participants “guessing” what the
researcher hopes to find
13. *Treatment Conditions
In experimental treatment, the researcher
physically intervenes to alter the conditions
experienced by the experimental unit.
Specifically the procedure would be-
*Identifying a treatment variable
*Identifying the conditions of the variable
*Manipulating the treatment conditions
14. *Steps in Conducting Experimental
Research
*Decide if any experiment addresses the research problem
*From a hypothesis to test Cause-and-Effect relationship
*Select an Experimental Unit and identify study
participants
*Select an Experimental Treatment and introduce it
*Choose a type of experimental design
*Conduct the experiment
*Organize and analyze the data
*Develop an experimental Research Report.
15. *Types of Experimental
Designs: Between Groups
*True Experiments
*Pre- and posttest
*Posttest Only
*Quasi Experiments
*Pre- and posttest
*Posttest Only
*Factorial Designs
16. *Types of Experimental
Designs: Within-Group or
Individual
*Time series experiments
*interrupted
*uninterrupted
*Repeated measures experiments
*Single-subject experiments
*A/B design
*Multiple baseline design
*Alternating treatments
17. *TRUE EXPERIMENTAL DESIGNS
*In true experimental designs the researchers have
complete control over the extraneous variables and can
predict confidently that the observed effect on the
dependent variable is only due to the manipulation of
independent variable.
*ESSENTIAL CHARACTERISTICS
Randomization
Control group
Experimental group
18. * RANDOMIZATION
*Means that every subject has an equal chance of being
assigned to experimental or control group.
*This is called random assignment of subjects.
*The process involves random assignment to different
groups.
*Randomization is used in true experimental designs to
minimize the threats of internal validity of the study
and eliminates the effects of extraneous variables on
the dependent variables.
19. *TYPES OF TRUE EXPERIMENTAL
DESIGNS
1. POST TEST ONLY DESIGN.
2. PRETEST-POST-TEST-ONLY
DESIGN.
20. *POST TEST ONLY DESIGN
*Is composed of two randomly assigned group -
experimental & control groups.
*Both the groups are not tested previous to the
introduction of an intervention.
*While treatment is implemented on the experimental
group only, post test observations are made on both
the groups.
*This design is helpful in situations where it is not
possible to pre treat the subjects.
21. *POST TEST ONLY DESIGN
l 21
EXPERI.
GROUP
RANDOM
ASSIGNMENT
CONT.
GROUP
POST
TEST
POST
TEST
22. *PRETEST-POST-TEST-ONLY
DESIGN
*In this design, subjects are randomly assigned to
either the experimental or control group.
*The effect of the dependent variable on both the
groups is seen before the treatment (pre test).
*Following this the treatment is carried out on
experimental group only.
*After treatment observation of dependent variable is
made on both the groups to examine the effect of the
manipulation of independent variable on dependent
variable.
23. *PRETEST –POST TEST ONLY
DESIGN
RANDOM
ASSIGNMENT
EXP GROUP
CONTROL
GROUP
TREATMENT POST
TEST
POST
TEST
PRE
TEST
PRE
TEST
24. *Quasi-experimental
designs
*These designs lack either random selection of
participants or random assignment to groups
*They lack some of the control of true experimental
designs, but are generally considered to be fine
*Example: Nonequivalent group design
25. *TYPES OF QUASI- EXPERIMENTAL
DESIGNS
1. POST TEST ONLY DESIGN.
2. PRETEST-POST-TEST-ONLY
DESIGN.
26. *POST TEST ONLY DESIGN
*Is composed of two non-randomly assigned/ intact/
selected group - experimental & control groups.
*Both the groups are not tested previous to the
introduction of an intervention.
*While treatment is implemented on the experimental
group only, post test observations are made on both
the groups.
*This design is helpful in situations where it is not
possible to pre treat the subjects.
27. *POST TEST ONLY DESIGN
l 27
SELECT
EXPERIMENTAL
GROUP
SELECT
CONTROL
GROUP
POST
TEST
POST
TEST
28. *PRETEST-POST-TEST-ONLY
DESIGN
*In this design, subjects are non-randomly assigned to
either the experimental or control group.
*The effect of the dependent variable on both the
groups is seen before the treatment (pre test).
*Following this the treatment is carried out on
experimental group only.
*After treatment observation of dependent variable is
made on both the groups to examine the effect of the
manipulation of independent variable on dependent
variable.
29. • The main weakness of this research design is the
internal validity is questioned from the interaction
between such variables as selection and maturation
or selection and testing. In the absence of
randomization, the possibility always exists that
some critical difference, not reflected in the
pretest, is operating to contaminate the posttest
data.
30. *PRETEST –POST TEST ONLY
DESIGN
SELECT
EXPERIMENTAL
GROUP
SELECT CONTROL
GROUP
EXPERIMENTAL
TREATMENT
POST
TEST
POST
TEST
PRE
TEST
PRE
TEST NO TREATMENT
31. *FACTORIAL DESIGN
*Here the researcher manipulates two or more
independent variables simultaneously to observe
their effects on the dependent variables.
*This design is particularly useful when there are more
than two independent variables to be tested.
32. *Within Group or Individual
Designs
*In any given experiment, the number of
participants may be limited and it may not be
possible to involve more than one group. In these
cases, researchers study a single group.
*So, the research design in which researchers study
a single group is called a within – group
experimental research design.
33. *A within – group experimental research design also can be
done with single individuals (within –individual experimental
research design).
*This type of design assumes several forms.
*Time Series Designs
*Repeated Measure Designs
*Single Subject Designs
34. *Time Series Design
*A time series design consists of studying one
group, over time, with multiple pretest and
posttest measures or observations made by the
researcher.
*When an experimental researcher has access to
only one group and can study them over a
period, a time series design is a good
experimental approach.
35. *Characteristics of Time
Series Design
*This design does not require access to large numbers of
participants.
*It is ideal for examining change in an entire system.
*However, this design is labor intensive because the
researcher needs to gather multiple measures. There are
two important variation of this design. They are –
*Interrupted time series design
*Equivalent time series design
36. *Interrupted Time Series
Design
*This procedure consists of studying one group,
obtaining multiple pretest measures for a period
of time, administering an intervention and then
measuring outcomes several times.
*The data analysis in this example, consists of
examining different scores between the pretests
and posttests or posttest-only scores.
37. *Interrupted Time Series Design
Select participants
for groups
Pretest measure
or observation
Pretest measure
or observation
Pretest measure
or observation
Intervention
Posttest measure
or observation
Posttest measure
or observation
Posttest measure
or observation
38. *Equivalent Time Series Design
*An equivalent time series design is, in which
the investigator alternates a treatment with a
posttest measure.
*The data analysis then consists of comparing
posttest measure or plotting them to discern
patterns in the data over time.
39. *Equivalent Time Series Design
Select participants
for groups
Measure
or observation
Measure
or observation
Intervention
Intervention
Measure or
observation
Intervention
Measure or
observation
40. *Repeated Measure Design
*Another experimental design that has the advantage of
employing only a single group is a Repeated Measure
Design.
*In this design all participants in a single group participate
in all experimental treatments, with each group
becoming its own control.
*The researcher compares a group’s performance under
one experimental treatment with its performance under
another experimental treatment.
*The experimenter decides on multiple treatments but
administers each separately to only one group.
41. *Repeated Measure Design
Select participants
for group
Measure
or observation
Experimental
Treatment #1
Measure or
observation
Experimental
Treatment #2
Measure or
observation
42. *Single Subject Design
*Single Subject Design involves the study of single
individuals, their observation over a baseline period
and the administration of an intervention.
*This design is also called as behavior analysis or within
subject research.
*The researcher studies the behavior of single
individuals rather than a group of subjects, with the
subject becoming its own control in the experiment.
*This is followed by another observation after the
intervention to determine if the treatment affects the
outcome.
43. *CONTINUE…
*The investigator seeks to determine if an intervention
impacts the behavior of a participants by observing
the individual over a prolonged period of time and
recording the behavior before and after the
intervention.
*The researcher assesses whether there is a
relationship between the treatment and the target
behavior or outcome.
44. *Characteristics of Single
Subject Design
*Prior to administering the intervention, the researcher
establishes a stable baseline of information about the
individuals behavior.
*The researcher repeatedly and frequently measures
behavior.
*After administering the intervention, the researcher
notes the pattern of behavior and plots them on a graph.
*In a graphic analysis of the data, the single subject
researcher plots behavior for specific individuals on a
graph.
45. *Advantages of Single Subject
Design
*Single Subject Design has the advantage to provide the data of a
single individual.
*It also controls many threats to internal validity.
*Assuming that the observer use the same standard procedures,
instrumentation
*When multiple treatments are used, the learning from one
intervention may affect the second intervention, and history
may be an issue since the experiment takes place over time.
*Without random assignment this is a quasi experimental rather
than an experimental design may not be a problem.
47. *A/B design
*An A/B design consists of observing and measuring
behavior during a trial period, administering an
intervention and observing and measuring the behavior
after the intervention.
*In this study, the researcher observes baseline behavior
and then employs an intervention of feedback to the
participants about their performance.
*The simplest design among Single Subject Design is A/B
design.
48. *Variations of A/B design
*A Variations of A/B design is A/B/A or a reversal design, in
which the researcher establishes a baseline behavior,
administers an intervention and then withdraws the
intervention and determines if the behavior returned to
the baseline level.
*Another Variations of A/B design is A/B/A withdrawal
design, in which researcher may implement one or more
treatments. But the withdrawing of the intervention may
have serious effects on the participants in the study,
raising an ethical issue for the researcher.
49. *Multiple Baseline Design
*A frequently used single subject design is the Multiple
Baseline Design, in which each participant receives an
experimental treatment at a different time.
*Researcher choose this design when the treatment cannot
be reversed and doing so would be unethical or injurious to
participants.
*Variation on this approach could involve different types of
behaviors for the participants or behaviors for the
participants in different settings.
*The result of this design may be less convincing than the
reversal design and it may introduce negative consequences
if the treatment is with-held for an extended period.
50. *Alternating treatments Design
*An Alternating treatments Design is a Single Subject Design in
which the researcher examines the relative effects of two or
more interventions and determines which intervention is the
more effective treatment on the outcome.
*After establishing a baseline of behavior, the researcher
implemented the two different experimental treatments and
plotted behavior after the treatments.
*In this type of design, potential problems with threats to
internal validity from treatment diffusion may result, but the
design permits a test of multiple treatments simultaneously to
determine their effects on outcomes.
51. Types of Within Group Experimental Design
Topics Time
Series
Repeated
Measures
Single
Subject
Random
Assignment
No No No
No. of groups/
ind. compared
One
Group
One
Group
One
Indivi.
No. of interventi-
-ons used
One/
More
Two/
More
One/
More
No. of times the
dependant varia-
-bles observed
After
each
interve
ntion
After
each
interventi
on
Multiple
Points
Controls used Group Covariate Indivi.
52. *LIMITATIONS
•Most often the results of experimental designs cannot be
replicated in studies conducted on humans due to ethical
problems.
•Many of the human variables neither have valid
measurable criteria nor instruments to measure them.
•In experimental studies conducted in natural settings like
a hospital or community, it is not possible to impose
control over extraneous variables.
•Experiments are often more impractical when the effect
of independent variable may require a lengthy period of
time before it can emerge as a response on the criterion
measures.
53. CONTINUE…
• It is very difficult to obtain permission from the participants.
• Because the size of the sample is kept small especially studies
involving humans, the representativeness of the findings of
such study is questionable.
• Though theoretically experimental designs can yields a greater
insights , yet practically many a times they are not possible in
human studies as humans & their parameters are complex.
• Participants can be influenced by environment
Those who participate in trials may be influenced by the
environment around them. As such, they might give answers
not based on how they truly feel but on what they think the
researcher wants to hear. Rather than thinking through what
they feel and think about a subject, a participant may just go
along with what they believe the researcher is trying to
achieve.
54. *WHEN AND WHERE DO WE USE
AN EXPERIMENTAL RESEARCH
*Commonly used in sciences such as sociology, psychology,
physics, chemistry, biology and medicine, experimental
research is a collection of research designs which make
use of manipulation and controlled testing in order to
understand casual processes. To determine the effect on a
dependent variable, one or more variables need to be
manipulated.
*The aim of experimental research is to predict
phenomenons . In most cases, an experiment is
constructed so that some kinds of causation can be
explained. Experimental research is helpful for society as
it helps improve everyday life.