SOCY 211 Lecture Notes - Lecture 11: Studentized Range Distribution, Statistical Significance, Type I And Type Ii Errors
Document Summary
10. 1 anova f-tests: single -factor anova. Comparing more than two groups in categorical data. Anova is a framework to test multiple questions while controlling type i error. Anova asks: is the variation among group means great than by chance alone: ho: all group means are equal. Ha: at least 2 of the group means aren"t equal: hypothesis testing. Anova partitions variation and uses and f-test. Group variation is the variation between the means of the groups and the grand mean. Under the null hypotheses, the ratio of group mean square to the error mean square should be 1. If p<0. 05, we reject the null hypothesis and conclude that there is a difference somewhere among the groups, but we can"t say where it is. 10. 2 anova assumptions: evaluating assumptions qualitatively. Residual variance is the same for all groups. Y-values represent random and independent observations: evaluating assumptions quantitatively. Residuals are normally distributed: shapiro-wilks test ho: residuals are normally distributed.