Weighted composite likelihood for linear mixed models in complex samples

Abstract

Fitting mixed models to complex survey data is a challenging problem. Most methods in the literature, including the most widely used one, require a close relationship between the model structure and the survey design. In this paper we present methods for fitting arbitrary mixed models to data from arbitrary survey designs. We support this with an implementation that allows for multilevel linear models and multistage designs without any assumptions about nesting of model and design, and that also allows for correlation structures such as those resulting from genetic relatedness. The estimation and inference approach uses weighted pairwise (composite) likelihood.