ANOVA
Used to compare the means of multiple groups on a single DV. However, this is a non-specific test and doesn’t explain where the differences lie.
ANOVA doesn’t consider patterns in data.
ANOVA Test Statistic
F ratio is a comparison of model variance and error variance. If the ratio is greater than 1, there is an effect.
Planned Contrasts
Method for breaking down how the groups in an ANOVA may differ. Theory driven and planned before conducting the analysis. Can also be used to assess patterns in data.
Rules for Choosing Contrasts
Three Rules
Rules for Coding Contrasts
Assumptions of ANOVA
Normality, no outliers, homogeneity of variance, linearity, independence.