Generalized Linear and Nonlinear Models for Correlated Data: Theory and Applications Using SAS

Part ILinear Models

2Marginal Linear Models—Normal Theory

2.1 The marginal linear model (LM)

2.2 Examples

2.3 Summary

In this chapter and the next, we examine various types of linear models used for the analysis of correlated response data assuming the data are normally distributed or at least approximately so. These two chapters are by no means intended to provide a comprehensive treatment of linear models for correlated response data. Indeed such texts as those by Verbeke and Molenberghs (1997), Davis (2002), Demidenko (2004), and Littell et. al. (2006) provide a far more in-depth treatment of such models, especially of linear mixed-effects models. Rather, our goals are to 1) provide a basic introduction to linear models; 2) provide several ...