Mixed-effects models incorporate both "fixed effects", which apply to an entire population or identified parts of it, and "random effects", which describe individual members of the population. A class of mixed models, called hierarchical linear models (HLMs) or multilevel models, is widely used in the social sciences. Linear mixed models for continuous data have been extended to generalized linear mixed models for binary and count data, and can be extended further.
Recent developments in computational methods, incorporated in the lme4 package for R, can fit these and more general forms of mixed models, including models with crossed random effects, say for both subject and stimulus.
This hands-on workshop will introduce mixed models and the lme4 package for fitting, analyzing and displaying such models. Although not required to benefit from the workshop, previous experience with R is recommended.
Douglas Bates has made important contributions to several areas of statistics, including nonlinear regression and mixed effects models. He is the author of the nlme and lme4 packages for R and a member of the R Core group of developers.