Chapter 11: The t Test for Two Related Samples

repeated measures design

2 scores are obtained for each individual; same subjects are used in both treatment conditions

characteristics of a repeated measures design

no risk of participants in each treatment group differing significantly from each other, requires fewer participants

t-statistic

same as one sample, except it is based on "difference scores" (D)

difference scores

D = x2 - x1; use D for variance, estimated standard of error

advantages of repeated measures

requires fewer subjects, reduces/eliminates influence over individual differences, allow us to look at changes over time

disadvantages of repeated measures

factors besides treatment may cause subject's score to change during the time b/w measurements, participation in first treatment may influence scores in second treatment (order effects)

how to address order effects

counterbalancing