Exam
Research Methods in Psychology
Repeated Measures Designs
1
Repeated Measures Designs
Each individual participates in each condition of the experiment
Completes the DV measure with each condition
Hence “repeated measures”
Also called “within-subject” design
Entire experiment is conducted “within” each subject
2
Repeated Measures Designs, continued
Advantages
No need to balance individual differences across conditions of experiment
Fewer participants needed
Convenient and efficient
Measure changes in participants’ behaviors over time
More sensitive design
3
Sensitivity
A sensitive experiment
Can detect effects of IV even when IV has small effect
“Error variation” is reduced
Same people participate in each condition
Variability due to individual differences eliminated
4
Practice Effects
Disadvantage: practice effects
People change as they are tested repeatedly.
Performance may improve over time.
People may become bored or tired as number of “trials” increases.
Practice effects become a potential confounding variable if not controlled.
5
Practice Effects, continued
Example
Suppose a researcher compares two different study methods, A and B.
Condition A: Participants use a highlighter while reading a text, then take a test on the material.
Condition B: Participants read a text and make up sample test questions and answers, then take a test on the material.
6
Practice Effects, continued
Suppose
All participants first experience Condition A and then Condition B
Results indicate test scores are higher in Condition A compared to Condition B
Confounding of IV with order of presentation
Can’t determine effect of IV
Practice effects (boredom, fatigue) may explain poorer performance in Condition B
7
Practice Effects, continued
Balance practice effects across conditions.
Counterbalance the order of conditions
Half of the participants do Condition A, then B
The remaining participants do Condition B, then A
Distribute practice effects equally across conditions.
Practice effects aren’t eliminated.
Balance, or average, practice effects across the conditions of the experiment.
8
Counterbalancing Practice Effects
Two types of repeated measures designs
Complete and Incomplete
Purpose of each type: counterbalance practice effects
9
Complete Repeated Measures Design
Balance practice effects within each participant.
Each participant experiences each condition several times.
Each participant forms a “complete experiment.”
Use different orders each time
Use when each condition is brief
e.g., simple judgments about stimuli
10
Complete Design, continued
Two methods for generating orders of conditions
Block randomization
ABBA counterbalancing
11
Complete Design, continued
Block randomization
Block = all conditions of an IV
e.g., 4 conditions: A, B, C, D (e.g., control; hand-held, hands-free, passenger)
Generate a random order of the block (ACBD)
Participant completes condition A, then C, then B, then D
Generate new random order for each time participant completes conditions of experiment
12
Complete Design, continued
Block randomization
In general, the number of blocks is equal to the number of times each condition is administered, and the size of each block is equal to the number of conditions.
Practice effects are averaged across the many presentations of the conditions
Requires many presentations to balance practice effects
13
Complete Design, continued
ABBA counterbalancing
Use when conditions are presented only a few times to each participant
Use random sequence of conditions (e.g., DACB)
Then present opposite of sequence (BCAD)
Repeat with new random sequence and opposite, etc.
Each condition has same amount of practice effects.
14
Complete Design, continued
Use ABBA counterbalancing only if practice effects are “linear”
Linear practice effects
Participants change in the same way with each presentation of a condition.
Nonlinear practice effects
Participants change dramatically with the administration of a condition (e.g., “aha”)
Confounding between practice effects and IV
Use block randomization
15
Complete Design, continued
Do not use ABBA counterbalancing when anticipation effects can occur.
Participants form expectations about which condition will appear next in sequence.
Responses may be influenced by expectations (not IV).
If anticipation effects are likely (e.g., conditions are predictable), use block randomization.
16
Incomplete Repeated Measures Design
Each participant experiences each IV condition once.
Balance practice effects across participants (not within).
General rule for balancing practice effects
Each IV condition must appear in each ordinal position (1st, 2nd, 3rd) equally often.
17
Incomplete Design, continued
Two techniques for balancing practice effects
All possible orders
Selected orders
18
Incomplete Design, continued
All possible orders
Use with 4 or fewer IV conditions (e.g., control; hand-held, hands-free, passenger)
2 conditions (A, B) → 2 possible orders: AB, BA
Randomly assign half of the participants to do condition A first, then B; other half: B then A
3 conditions (A, B, C) → 6 possible orders
Randomly assign participants to one of the six orders
4 conditions (A, B, C, D) → 24 possible orders
Need at least 1 participant randomly assigned to each order
19
Incomplete Design, continued
Selected orders
Select particular orders of conditions to balance practice effects
Two methods
Latin Square
Random starting order with rotation
Each IV condition appears in each ordinal position exactly once.
Randomly assign each participant to one of the orders of conditions.
20
Latin Square (example)
We select the number of orders that is some multiple of the number of conditions.
Each condition appears in each ordinal position once to balance practice effects.
Order of Conditions
1st 2nd 3rd 4th
A B D C
B C A D
C D B A
D A C B
Incomplete Design, continued
21
Incomplete Design, continued
Another advantage of Latin Square:
1st 2nd 3rd 4th
A B D C
B C A D
C D B A
D A C B
Each condition precedes and follows every other condition once (e.g., AB and BA, BC and CB)
This helps control for potential order effects (p. 258)
22
Incomplete Design, continued
Random starting order with rotation
Generate random order of conditions (ABCD)
Rotation: move each condition one position
1st 2nd 3rd 4th
A B C D
B C D A
C D A B
D A B C
Each condition appears in each ordinal position
Order of conditions is not balanced
23
The Problem of Differential Transfer
Do not use repeated measures designs when differential transfer is possible.
Effects of one condition persist and affect participants’ experience of subsequent conditions (problem solving experiment)
Use independent groups design instead
24