IMPS 2008: Workshops

Pre-Conference Workshops, Sunday June 29th

Models for Longitudinal and Incomplete Data	Geert Molenberghs - U. Hasselt Geert Verbeke - K.U.Leuven, Belgium
(8:30am to 12:30pm)
From the modeler's and applications' perspectives, linear mixed models for continuous hierarchical data, as well as marginal (GEE) and mixed-effects models for non-Gaussian data, are presented. When analyzing hierarchical and longitudinal data, one is often confronted with missing observations. Issues arising and ways to overcome them will be discussed. The developments are illustrated using worked examples; their software implementations are discussed in generic terms.

Fitting Mixed-effects Models Using the lme4 Package in R	Douglas Bates - Univ. Wisconsin
(1:30pm to 5:30pm)
This workshop will describe the use of the lme4 package for fitting and analyzing mixed models in some common settings, such as longitudinal data, and other types of data for which mixed models may be appropriate but have not been widely used because of computational barriers. Various models will be discussed, including item response models, also for data with random effects for crossed factors, such as a generalized nonlinear mixed model with crossed random effects, with random effects for student abilities and for item difficulties and discriminations.

Advanced Latent Variable Mixture Modeling Using Mplus	Bengt Muthén - UCLA Linda Muthén - Muthén & Muthén
(8:30am to 12:30pm, continuing 1:30pm to 5:30pm)
The workshop focuses on models that use categorical latent variables, either alone or together with continuous latent variables, based on the general modeling framework of the Mplus program (www.statmodel.com). The theme is latent classes corresponding to different groups of individuals, and to different groups of level 2 units such as schools in multilevel data, as well as latent trajectory classes corresponding to different types of development. An overview of conventional and new techniques is given. Issues of model specification, identification, estimation, testing, and model modification are discussed. Several examples are examined, input setups are provided and output is used for interpretation of analysis results.