Lecture 11: Experimental Design and Analysis II

Question 1

Correlated-Groups Designs

Answer 1

Designs where the subjects in the experimental and control groups are related. Includes repeated-measures designs and matched-subjects designs.

Question 2

Repeated-measures Experimental Designs

Answer 2

Also referred to as within-subjects designs. Repeatedly taking measures on the same individuals. A random sample of participants are selected, but random assignment is not required as participants take part in all conditions

Question 3

Repeated-measures Experimental Designs advantages

Answer 3

Requires less participants

Less time consuming

Increased statistical power (minimised variability due to individual differences)

Question 4

Repeated-measures Experimental Designs disadvantages

Answer 4

Internal validity confounds

Order effects (can be minimised by counterbalancing)

Question 5

Matched-Subjects Experimental Designs

Answer 5

Share characteristics of both between-subjects and
within-subjects. Different participants are used in each condition. Participants between conditions are matched on characteristics of interest. E.g;, IQ, weight, height, etc. Addresses concern of carryover effects

Question 6

Matched-Subjects Experimental Designs advantages

Answer 6

Testing effects and demand characteristics are minimised

Groups are more equivalent than independent measures

Data is treated with same statistics as repeated measures

Question 7

Matched-Subjects Experimental Designs disadvantages

Answer 7

More participants needed

If one participant drops out – loss of pair

The matching process

Question 8

t-test for repeated measures or matched subjects

Answer 8

It compares means of subjects in two groups. Same people are in each group (repeated-measures), or are matched (matched-subjects). Test indicates if there is a difference in the sample means and whether this difference is greater than what would be expected by chance (i.e., statistically significant). Convert two scores for each person into one score (we compute a difference score).

Question 9

Difference scores

Answer 9

We compute a difference score for each person by
subtracting one score from their other score

Null: No difference between the scores

Alternate: There is a difference between the scores

Question 10

Repeated Measures t-test: Example

Answer 10

You’ll have to look at the slides for a diagram, graph and example explanation