A sequential reduction method for inference in generalized linear mixed models

作者：Ogden Helen E^*

来源：Electronic Journal of Statistics, 2015, 9(1): 135-152.

DOI：10.1214/15-EJS991

• Graphical model
• intractable likelihood
• Laplace approximation
• pairwise comparison
• sparse grid interpolation

The likelihood for the parameters of a generalized linear mixed model involves an integral which may be of very high dimension. Because of this intractability, many approximations to the likelihood have been proposed, but all can fail when the model is sparse, in that there is only a small amount of information available on each random effect. The sequential reduction method described in this paper exploits the dependence structure of the posterior distribution of the random effects to reduce substantially the cost of finding an accurate approximation to the likelihood in models with sparse structure.

• 出版日期2015