In Chapters 2, 3, and 5 through 9 we focused on presenting multiple regression/correlation analysis as a general data analytic system. We have illuminated the flexibility and power of this analytical tool to answer a wide variety of research questions of interest to behavioral scientists. Our presentation has progressed from simple to complex models, from linear to nonlinear and interactive relationships, and from quantitative to qualitative to combinations of quantitative and qualitative IVs. The sole exception to this progression was in Chapter 4. There we considered problems that arise from the violation of the assumptions underlying multiple regression analysis. We considered graphical and statistical methods of detecting such violations and methods of solving these problems when they are detected. These procedures help researchers gain a fuller understanding of their data so that they do not report misleading results. The present chapter continues this theme, considering two problems in regression analysis that were not considered in Chapter 4.