PSYCH 210 Study Guide - John Tukey, Alternative Hypothesis, Repeated Measures Design
Document Summary
You use anova when you have three or more groups. You would be inflating alpha and your type i error would increase, this is bad. The degrees of freedom are the same, and are used in both anova and t-tests (i. e. t=df=18, anova=f(1,18)) So you can identify exactly where the difference is. How does the f-ratio differ for repeated-measures anova compared with independent-measures anova. More than one sample, but you match them on age, gender ect. There is no effect of sleep aid on hours of sleep. H1: at least one population mean is difference. P = sum of scores for each participant k = number of treatment conditions n = number of scores in each treatment condition. N = total number of scores in the study. T = sum of scores for each treatment condition. G = sum of all scores in the study. Remove variability from factors other than treatment effect.
