Elective -educational research -Unit-3 -Experimental research:

Nature, Definitions:
Experiment refers to the process of studying the effect of independent variables on the dependent variables under the controlled conditions.
According to Best (1977) Experimental research is the description and analysis of what will be or what will occur , under carefully controlled conditions.

Variables are the conditions or characteristics that the experimenter manipulates, controls or observes.
Variables are constructs which varies according to the conditions.
Variables could be an I.Q, a particular teaching method, teaching material, sex, a particular course, temperature, aptitude, attitude, aggression, aspiration, learning style, self esteem, and teaching style and so on.

Independent variables:
The independent variables are the conditions or characteristics that the experimenter manipulates or controls in his or her attempt to ascertain their relationship to observed phenomena.
Dependent variables: The dependent variables are conditions or characteristics that appear, disappear or change as the experimenter introduces, removes or changes independent variables.
Independent variables are of two types
Organismic variables or attributive variables: these variables cannot be manipulated by the experimenter. For instance, Sex, I.Q., race, age
Treatment variables: these are the variables that the experimenter manipulates and to which he or she assigns subjects. For instance, teaching method, teaching material, strategy etc.
Confounding variables: confounding variables are those aspects of study or sample that might influence the dependent variables (outcome measure) and whose effect may be confused with the effects of the independent variable.
Confounding variables are of two types: Intervening and extraneous variables

Extraneous variables: they are those uncontrolled variables (variables not controlled by the experimenter) that may have significant influence on the results of the study.
Intervening variables:
Certain variables that cannot be controlled or measured directly have an important effect on the outcome. These modifying variables intervene between the cause and the effect is known as intervening variables. For example anxiety, fatigues, motivation on the part of the subjects during the treatment have their impact on the results of the study.

Characteristics of experimental research
Control :
Creating an environment so that the effects of the desired variables can be measured objectively. Control can reduce the effect of extraneous variables to the minimum.
Manipulation:
Increasing or decreasing or removing independent variables to study the effect on dependent variables
Observation:
Manipulating the independent variables and carefully observing and recording the effects of this manipulation on the dependent variables or some measurable behavior of the sample.
Replication:
Replication of the study to take care of lacunae observed in the study.

Steps of experimental research
· Introduction-conceptual framework of the selected problem of the study
· Review of the related literature
· Rationale of the study
· Research questions
· Statement of the problems
· Operationalization of the terms/variables
· Extraneous variables
· Hypothesis
· Population
· Sample
· Data collection tools
· Data analysis techniques
· Reference

Designs of experimental research

Experimental design is the blue print of the procedures that enable the researcher to test hypotheses by reaching valid conclusions about relationships between independent variables and dependent variables. Selection of a particular design is based on the purposes of the experiment, the type of variables to be manipulated, and the conditions or limiting factors under which it is conducted. The design deals with such practical problems as how subjects are to be assigned to experimental and control groups , the way variables are to be manipulated and controlled , the way extraneous variables are to be controlled , how observations are to be made, and the type of statistical analysis to be employed in interpreting the data relationships.
Campbell and Stanley (1966) has used following symbol system for discussing experimental designs
R random assignment of subjects to groups or treatments
X exposure of a group to an experimental (treatment) variable
C exposure of a group to the control condition
O observation or test administered
Following are the research designs
1 Pre-experimental design: Here there is no control group. Even if it there is no way of equating the group. Following are the sub research designs under it.

1.1 The one group, pre test-post design
O1 X O2 ,
O1 =Pre test O2 = Post test

Effectiveness of the experiment is measured by finding the difference between the mean scores of pre test and post test.
1.2 The static group comparison design

X O
C O

This design compares 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 groups, a very serious limitation.

2 true experimental design:
In a true experimental design, the equivalence of the experimental and control groups is provided through random assignments of subjects to experimental and control treatments.

2.1 The post test only –equivalent –groups designs
R X O1
R C O2

Here the subjects are assigned through random way (R) to both the groups and groups are thus equated. Then one group is given the treatment (X) and the other is the controlled group (C) which is not given the treatment or may be given the treatment other that the one used for experimental group. At the end of the treatment, tests are administered (O1 for experimental group and O2 for control group). The difference between the mean scores of both the groups are calculated through‘t’ test for statistical significance.

2.2 The pre test post test equivalent group design
R O1 X O2 O1 O3 = pre test scores
R O3 C O4 O2 O4 = post test scores

Here the subjects are assigned through random way (R) to both the groups and groups are thus equated. The pre test scores are conducted for both the groups and the difference in the mean scores is measured. Then one group is given the treatment (X) and the other is the controlled group (C) which is not given the treatment or may be given the treatment other that the one used for experimental group. Afterwards the post tests are conducted for both the groups and the difference between the mean scores are calculated.

3. Quasi experimental design
The pretest-post test non equivalent groups design
O1 X O2 O1 O3=pre tests
O3 C O4 O2 O4= post tests
The entire procedure in this design is same as mentioned above in 2.2 except that the groups are not equated.