ABSTRACT
This chapter introduces the structure of the general linear model and explores the structure to classify the linear models. It reviews the multivariate normal distribution which forms the basis for most of the hypothesis testing theory of the linear model, along with a general approach to hypothesis testing. The generation of multivariate normal data, the construction of Quantile-Quantile (Q-Q) plots, chi-square plots, scatter plots, and data transformation procedures are reviewed and illustrated to evaluate normality. In hypothesis testing of univariate and multivariate linear models, the assumption of multivariate normality is made. One step in evaluating multivariate normality of a random vector is to evaluate the univariate normality of it components. Three dimensional scatter plots of multivariate data often help with the visualization of data. Q-Q plots are plots of the observed, ordered quantile versus the quantile values expected if the observed data are normally distributed.
