@article {wu_generalized_2006, title = {Generalized linear mixed models with informative dropouts and missing covariates}, journal = {Metrika}, volume = {66}, number = {1}, year = {2006}, month = {aug}, pages = {1{\textendash}18}, abstract = {Generalized linear mixed models (GLMM) are useful in many longitudinal data analyses. In the presence of informative dropouts and missing covariates, however, standard complete-data methods may not be applicable. In this article, we consider a likelihood method and an approximate method for GLMM with informative dropouts and missing covariates. The methods are implemented by Monte{\textendash}Carlo EM algorithms combined with Gibbs sampler. The approximate method may lead to inconsistent estimators but is computationally more efficient than the likelihood method. The two methods are evaluated via a simulation study for longitudinal binary data, and appear to perform reasonably well. A dataset on mental distress is analyzed in details.}, keywords = {Economic Theory, general, Gibbs sampling, Linearization, Probability Theory and Stochastic Processes, PX-EM algorithm, Rejection sampling, Statistics, Statistics for Business/Economics/Mathematical Finance/Insurance}, issn = {0026-1335, 1435-926X}, doi = {10.1007/s00184-006-0083-6}, url = {http://link.springer.com/article/10.1007/s00184-006-0083-6}, author = {Wu, Kunling and WU, LANG} }