experimental research designs. ltst.ppt
TRANSCRIPT
PRESENTED BY
AADAB MUSHRIBF15-3356, M.PHIL IN EDUCATION
SUPERVISOR: DR. SYED MANZAR ABBAS SHAH, ASSISTANT PROFESSOR, PH.D. LLU .
Experimental Research Designs
EXPERIMENTAL RESEARCH DESIGNS
An experiment typically involves a comparison of two groups (although some experimental studies have only one group or even three or more groups).
Single-variable designs involves one independent variable (which is manipulated) and are classified as under:-
I. Weak experimental research II. True experimental III. Quasi-experimental
WEAK EXPERIMENTAL DESIGNS
Designs that are “weak” don’t have built-in controls for threats to internal validity.
Four Examples of Pre-Experimental Designs are as under:-1. One-Shot Case Study Design2. One-Group Pretest-Posttest Design3. Static -Group Comparison Design4. Static-Group pretest-posttest Design
WEAK EXPERIMENTAL DESIGNS1. THE ONE-SHOT CASE STUDY DESIGN
In this design a single group is exposed to a treatment or event
and a dependent variable is subsequently observed (measured) in
order to asses the effect of the treatment.The One-Shot Case Study Design
X O Treatment Observation (Dependent Variable)
The most obvious weakness of this design is its absence of any control. The researcher has no way of knowing if the result obtained at O. Because the group has not been pretested in any way..
WEAK EXPERIMENTAL DESIGNS2. THE ONE-GROUP PRETEST-POSTTEST DESIGN
In this design, a single group is measured or observed not only after being exposed to a treatment of some sort, but also before.
O X O Pretest Treatment Posttest
This design is better than the one-shot case study, but it is still weak.
WEAK EXPERIMENTAL DESIGNS3. THE STATIC-GROUP COMPARISON DESIGNIn this design, two already existing, or intact, group, groups are used. This design is some times called a nonequivalent control design group design. X OOLine indicates that 02 groups being compared are already formed. X symbolizes the experimental treatment and blank space indicates that the “control” group doesn’t receive the experimental treatment.
WEAK EXPERIMENTAL DESIGNS 4.THE STATIC-GROUP PRETEST-POSTTEST
DESIGNThe static-group pretest-postest design differs from the static-group comparison only in that a pretest is given to both group. Diagram is as follows:
O X OO OIn analyzing the data, each individual’s pretest scores is subtracted from his/her posttest scores, thus permitting analysis of “gain” or “change”.
In weak designs, it is the strongest design.
TRUE-EXPERIMENTAL DESIGNS
The essential ingredient of a true experimental design is that subject are randomly assigned to treatment groups. Randomly assignment is a powerful technique for controlling the subject characteristics threat to internal validity. Its types are as under:The Randomized Posttest-Only Control Group Design The Randomized Pretest-Posttest Control Group Design The Randomized Solomon Four-Group Design
TRUE-EXPERIMENTAL DESIGNS1, THE RANDOMIZED POSTTEST-ONLY CONTROL GROUP DESIGN
This design involves two groups, both of which are formed by random assignment. One group receives the experimental treatment while the other does not, and then both groups are posttested on the dependent variable.Treatment Group R X OControl Group R C O
In this design, the control of certain threats is excellent.
This is perhaps the best of all designs to use in an experimental study, provided there are at least 30 subjects in each group.
TRUE-EXPERIMENTAL DESIGNS2. THE RANDOMIZED PRETEST-POSTTEST CONTROL GROUP DESIGN
The Randomized Pretest-Posttest Control Group Design differs from the Randomized posttest-only control group design solely in the use of a pretest. 02 groups of subjects are used, with both groups being measured or observed twice. The 1st measurement serves as pretest, the 2nd as the posttest. Random Assignment is used to form the groups. The measurement or observations are collected at the same time for both groups.Treatment Group R O X OControl Group R O C O
TRUE-EXPERIMENTAL DESIGNS3. THE RANDOMIZED SOLOMON FOUR-GROUP
DESIGN
The Randomized Solomon Four-Group Design is an attempt to eliminate the possible effect of a pretest. It involves random assignment of subjects to four groups, with two of the groups being pretested and two not. One of the pretested group and one of the unpretested groups is exposed to the experimental treatment. All four groups are then posttested.
Continued.
TRUE-EXPERIMENTAL DESIGNS3. THE RANDOMIZED SOLOMON FOUR-GROUP
DESIGN
Cont….Treatment group R O X OControl Group R O C OTreatment Group R X OControl Group R C O
A weakness of this design is that it requires a large sample because subjects must be as signed to four groups
QUASI-EXPERIMENTAL DESIGNS
Quasi-experimental designs do not include the use of random assignment. Researchers who employ these designs rely instead on other techniques to control threats to internal validity. The Matching-Only Design The Counterbalanced Design The Time Series Design
QUASI-EXPERIMENTAL DESIGNS
1.THE MATCHING ONLY DESIGNThis design differs from random assignment with matching only in the fact that random assignment is not used.
The Matching-only postest-only Control group DesignTreatment group.M X OControl Group M C O
The Matching-only pretest-Posttest only Control group Design
Treatment group. M O X OControl GroupM O C O
QUASI-EXPERIMENTAL DESIGNS
2.THE COUNTERBALANCED DESIGN
This design represent another technique for equating experimental and comparison groups. In this design, each group is exposed to all treatments, however many there are, but in a different order. Any number of treatments may be involved.
Group I X1 O X2 O X3 OGroup II X2 O X3 O X1 OGroup III X3 O X1 O X2 O
QUASI-EXPERIMENTAL DESIGNS TIME SERIES DESIGN
The typical pre-and posttest designs examined up to now involves observations or measurements taken immediately before and after treatment . A time series design, however involves repeated measurements or observations over a period of time both before and after treatment.O1 O2 O3 O4 O5 X O6 O7 O8 O9
O10
The effectiveness of the treatment in a time-series design is basically determined by analyzing the pattern of test scores that results from the several tests.
QUASI-EXPERIMENTAL DESIGNS
FACTORIAL DESIGNFactorial Designs involves two or more independent variables, at least one of which is manipulated by the researcher. The 2x2 is the simplest factorial design. Factorial designs rarely include more than three factors.A factorial design is used to test whether the effects of an independent variable are generalizable across all levels or whether the effects are specific to particular levels (i.e., there is an interaction between the variables.)
FACTORIAL DESIGNThis design extend the number of relationship that may be examined in an experimental study. They are essentially modifications of either the posttest-only control group or pretest-posttest control group designs, which permit the investigation of additional independent variables.Another value of a factorial design is that it allows a researcher to study the interaction of an independent variable with one or more other variables, sometimes called moderator variables.
FACTORIAL DESIGNCont…..moderator variables may be either treatment variables or subject characteristic variable.Treatment group R O X YI OControl Group R O C YI
OTreatment Group R O X Y OControl Group R O C Y
O