Nov 22, 2010 Ch.8

Pretest-Posttest Design

= A pretest is given before the experimental manipulation is introduced to make sure groups are

equivalent at the beginning of the experiment

Advantages of the pretest-posttest design

-Mortality (dropout factor)

-Assess equivalency of groups with small sample size

-Can use to select participants for the experiment

Disadvantages of the pretest-posttest design

-Time consuming and awkward to administer

-Sensitize participants to what is being studied

-Demand characteristics

-Reduces external validity

No Pretest effect:

Results for posttest only and pretest-posttest conditions have no significant differences in both control and

experimental groups

Repeated Measures Design

Advantages

-Fewer participants

-Extremely sensitive to statistical differences

-Conditions are identical because person is own control group

Disadvantage

-‘Carry over’ effects

-Practice effect

- Fatigue effect

www.notesolution.com

-Contrast effect

-Habituation (reduced responsiveness)

-Sensitization (stronger response)

-Adaptation (e.g. develops tolerance)

Issues to consider in repeated measures designs

1. Counterbalancing(Changing orders for experiment for studies to control for order effect)

-Complete counterbalancing

-Latin squares

Constructing Latin squares

Determines orders of N number of conditions

4 conditions=4 orders

8 conditions=8 orders

Each condition or groups appears once at each order and each condition precedes and

follows each other condition one time

*Remember formula for first row!! Then continue using row.

Need 2 Latin squares for odd number

1. Determine the number of conditions, and use letters of the alphabet to represent

them: ABCDEF for six conditions

2. Determine the order for the first row, using the following ordering:

AB L C L-1 D L-2 E etc…(L=final condition)

What would order for six conditions be?

www.notesolution.com

## Document Summary

= a pretest is given before the experimental manipulation is introduced to make sure groups are equivalent at the beginning of the experiment. Assess equivalency of groups with small sample size. Can use to select participants for the experiment. Results for posttest only and pretest-posttest conditions have no significant differences in both control and experimental groups. Conditions are identical because person is own control group. issues to consider in repeated measures designs: counterbalancing(changing orders for experiment for studies to control for order effect) Each condition or groups appears once at each order and each condition precedes and follows each other condition one time. Need 2 latin squares for odd number: determine the number of conditions, and use letters of the alphabet to represent them: abcdef for six conditions, determine the order for the first row, using the following ordering: Ab l c l-1 d l-2 e etc (l=final condition) What would order for six conditions be? www. notesolution. com.