Abstract: | The interaction structure analysis (ISA) is proposed as a nonparametric procedure for the evaluation of uni- and multivariate analysis of variance models. Main effects and interactions of (independent) treatment variables are replaced by interaction-types where types are defined as those treatment-response combinations which occur significantly more often than expected under a null hypothesis (Ho) of no treatment effects. The application of ISA and the typological interpretation of ISA results are illustrated for an ANOVA design from toxicology and for a MANOVA design from psychopharmacology. |