ABSTRACT

In Chapter 4, we introduced a simple additive linear model to describe the effects of a single explanatory factor. The ensuing statistical analysis is based on the assumption that this additive form of model is true, and also on the assumptions about the properties of the model deviations given in Section 4.1. Conclusions from the statistical analysis are valid only if these assumptions are consistent with the properties of the data. In this chapter, we describe some simple diagnostic tools that can be used to check the assumptions underlying analysis of variance.