Unit 7

Research Designs
Research design is the blue print of the procedures that enable the
researcher to test hypotheses by reaching valid conclusions about
relationship between independent and dependent variables.
1. How subjects are to be assigned to experimental and control group
2. The way variable are to be manipulated and controlled, the way the
extraneous variables are to be controlled
3. How observations are to be made
4. The type of statistical analysis to be employed in interpreting data
relationship
Types of Experimental Designs
1. Pre-experimental design: the least effective, for it provides either
no control group or no way of equating groups that are used
2. True-experimental design: employs randomization to provide for

control of the equivalence of groups and exposure to treatment
3. Quasi-experimental design: uses ready made groups and provides

less satisfactory degree of control, used only when randomization is not
feasible
We have to follow the following symbols
R Random assignment of subjects to groups or treatment
X Exposure of groups to an experimental (treatment) variable
C Exposure of a group to the control or placebo condition
O observation of test administration

E Experimental Group
Pre- Experimental Designs
1. The one shot case study:
a) It involves one group only
b) It is exposed to treatment ( X )
c) The group is then post tested ( O )
X O
Carefully studied results of a treatment are compared with a general
expectation of what would have happened if the treatment had not
been applied. The design provides the weakest basis for generalization
2. The one group, pre-test post-test Design:
a) this design involve one group

b) The group is pre teste ( O1 )
c) Then the group is exposed to treatment ( X )
d) The group is post tested ( O2 )
e) The scores of pre and post test are compared
O1 X O2
Here O1 is pre test O2 is post test
This design provides some improvement over the first, for the effect of the
treatment are judged by the difference between the pre test and post test scores.
No comparison with control group is provided
3. The static-group Comparison Design
a) This design involve two groups (control and experimental)
b) Experimental group receives new treatment
c) Control group receives no treatment
d) Both groups are post tested
X O
C O
This design compare the status of a group that has received an experimental
treatment with one that has not. There is no provision for establishing the
equivalence of the experimental and control group, a serious limitation.
True Experimental Designs
In true experiment the equivalence of the experimental and control group is
provided by the random assignment of subjects to experimental and control group.
1. The post-test only, Equivalent Group Design
a) There is no pre test
b) It involve two groups
c) Subjects are randomly assigned to Experimental and Control group
d) Experimental group is exposed to independent variable
e) Control group receives no treatment
f) Both the groups are post tested
R O1
R O2
True Experimental Designs (Cont.)
This design is one of the most effective in minimizing the threats to
experimental validity. It differ from the static group comparison design
in that experimental and control groups are equated by random
assignment.
At the conclusion of the experimental period the difference between
the mean test scores of the experimental and control groups are
subjected to a test of statistical significance, a t-test or an analysis of
variance.
2. The Pretest Posttest Equivalent Group Design
a) This design involves at least two groups

b) Both groups are formed by random assignment
c) Both groups are administered a Pre test
d) Experimental group receives new treatment
e) Control groups receives usual treatment
f) Both groups are post tested
g) Post test scores are compared to determine the effectiveness of
treatment
Rc O1 Re O2 (Pretest)
Rc O3 Re X O4 (Post test)
Rc Randomly selected control group

Re Randomly selected experimental group
This design is similar to the previously described design, except the pre
tests are administered before the application of the experimental and
control treatments and post tests at the end of the treatment period.
Experimental and control groups are formed and equated on the basis
of the pretest.
The effect of treatment is determined on the posttest scores by
applying a test of significance.
This is a strong design, but there may be a possibility of the influence of
the effect of testing and interaction with the experimental variable.
3. The Solomon Four Group Design
a) Subjects are randomly assigned to four groups

b) Two groups receives the experimental treatment (X)
c) One experimental group underwent pretest (O1)
d) Two control groups do not receive any treatment
e) One control group underwent pretest (O3)
f) All four groups receive post tests (O2, O4, O5, O6)
R O1 X O2
R O3 X O4
R X O5
R X O6
This design is really a combination of two group designs previously
described, the post test only and pretest posttest design. Analysis of
variance is used to compare the four posttest scores, Analysis of
covariance to compare gains in O2 and O4.
Because the design provides for two simultaneous experiments, the
advantages of a replication are incorporated. A major difficulty is
finding enough subjects to assign randomly to four equivalent groups
Qusai-Experimental Designs
These designs are ready mad groups. These designs provide control of
when and to whom the measurement is applied, but because random
assignment to experimental and control treatment has not been
applied, the equivalence of the groups is not assured.
Qusai-Experimental Designs (Cont)
1. The Pretest-Posttest Nonequivalent Groups design
a) ready made groups or intact classes are used (no random
assignment of subjects)
b) This design involve two groups (experimental and control group)
c) Both groups are pretested
d) New treatment to experimental group no treatment to control
e)Both groups are post tested
O1 X O2 O1 O3 = Pretests
O3 C O4 O2 O4 = Posttests
This design is often used in classroom experiments when experimental

and control groups are such naturally assembled groups as intact
classes, which may be similar. The difference between the mean of the
O1 and O2 scores and the difference between the mean of the O3 and
O4 scores (mean gain scores) are tested for statistical significance.
Analysis of covariance may also be used.
2. The time series Design
a) This design involves only one group
b) Group is repeatedly pretested
c) Experimental variable is introduced
d) Group is repeatedly posttested
At periodic intervals, observations (measurements) are applied to

individuals or groups. An experimental variable (X) is introduced, and
its effect may be judged by the change or gain from the measurement
before to the one immediately after its introduction. The purpose of
the series of measurements before and after the intervention or
treatment is to demonstrate little or no change except immediately
after the intervention.
in the time series experiment design, a measured change or gain from
observation 4 to observation 5 would indicate that treatment had an effect.
This design is particularly sensitive to the failure to the control the
extraneous variable, history, for it is possible that some distracting
simultaneous event at the time of the intervention would provide a rival
hypothesis for the change.
O1 O2 O3 O4 X O5 O6 O7 O8
The diagram showing one X and several Os does not necessarily represent
the relative number of sessions for each. It may be that each O represents
one measurement while the single X represent an intervention of several
weeks. While it is better to have several observations, as shown, it is not
always possible to have this many.

Unit 7

Uploaded by

Copyright:

Available Formats

Unit 7

Uploaded by

Document Information

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Unit 7

Uploaded by

Copyright:

Available Formats

Research Designs

2. True-experimental design: employs randomization to provide for

3. Quasi-experimental design: uses ready made groups and provides

X Exposure of groups to an experimental (treatment) variable

C Exposure of a group to the control or placebo condition

O observation of test administration

a) this design involve one group

a) This design involves at least two groups

Rc Randomly selected control group

a) Subjects are randomly assigned to four groups

This design is often used in classroom experiments when experimental

At periodic intervals, observations (measurements) are applied to

You might also like

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.