Analysis of Variance and Covariance
This chapter will be concerned with the analysis of designed experiments in medical investigations. Typically, such experiments involve a numeric response variable and one or more categorical variables (factors) that are typically under the control of the experimenter, although this is not always so. In addition, it is often the case that other continuous variables need to be included in the analysis. The relevant procedures for handling such studies are analysis of variance (ANOVA) and analysis of covariance (ANCOVA), and it is these that will be discussed in this chapter.