PSYC2203 Chapter Notes - Chapter 9: John Tukey, Multiple Comparisons Problem, Squared Deviations From The Mean
Document Summary
Multiple t tests: to compare 3 or more independent sample means, would could just perform a series of independent t tests comparing each group mean to every other group mean. This is the numerator of the f value: to calculate the f value, the msb is divided by the msw. Different post-hoc test are better than others in particular circumstances (e. g. , if the sample sizes are unequal, the variances between the groups are unequal, you want a particularly conservative or liberal test of statistical significance, etc. ) In this textbook we only discuss tukey hsd tests: the tukey test is sort of like a series of independent t tests in which each group in the. Effect size: the effect size used in anova is the eta squared statistic, the eta squared reveals the percentage of variance in the dependent variable that is explained by the independent variable.