3Linear Mixed-Effects Models—Normal Theory
3.1 The linear mixed-effects (LME) model
Within linear models, there are two distinct stochastic mechanisms for determining the overall correlation structure associated with repeated measurements and/or clustered data. In the marginal linear model of the preceding chapter, we account for correlation among observations from the same individual or unit by specifying a within-unit random error vector and its covariance structure. This approach assumes that random error vectors between units are independently distributed according to a multivariate normal distribution that varies between units only its dimension. In the repeated measurements setting, for example, we might regard ...
Get Generalized Linear and Nonlinear Models for Correlated Data: Theory and Applications Using SAS now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
