Chapter 9: Within Subjects Design

Question 1

How to calculate the F ratio for a Within Subjects design?

Answer 1

F=(condition effects+error)/error

Question 2

What are the threats to internal validity in a within subjects design?

Answer 2

Confounding environmental variables
Def→ Any characteristic in the environment that may differ between treatment conditions
- ex: lightning, noises
- may cause differences in score between two conditions
- may lead to a confound
Can control it by
- Standardizing it→ holding constant the environment
- Matching across conditions
- Randomization

Confounding time-related factors->Big 5
- History, Maturation, Instrumentation, Regression toward the mean, Testing effects

Question 3

What are the two types of testing effects?

Answer 3

• carryover effects→ one manipulation produce persistent consequences influencing the participants’ response to subsequent manipulations
• progressive error→ Changes to behaviour/performance that are related to general experience in research study (practice effects and fatigue effects)

Question 4

What are the different types of counterbalancing?

Answer 4

Complete counterbalancing→ All possible treatment orders are used equally often
- N!→ 3! = 1x2x3= 6 possibilities
- must be equal numbers of participants in each counterbalanced order
—>don’t eliminate order effects BUT control for them

Latin-Square Counterbalancing
Each condition occurs equally often in each order in the experiment
- don’t need all possibilities BUT simply make sure that each conditions occurs once in each order
- ex: ABC, BCA, CAB → only need 3 order instead of 6 possible orders

Partial counterbalancing
Each condition is preceded and succeeded equally often by the same conditions
- ex→ Condition A is preceded by Condition D and is succeeded by Condition B

Question 5

What are the advantages of a within subjects design?

Answer 5

Need fewer participants
Eliminates problems of individuals differences
Increase chances of detecting treatment effect

Question 6

What are the disadvantages of a within subjects design?

Answer 6

Not suitable when carry-over effects are expected
Participant attrition might be a problem
- change sample size and exaggerate volunteer bias
Ordering of conditions can be time-consuming and require many participants
- does not eliminate order effects