A0288
Title: Optimal designs for generalized linear mixed models
Authors: John Stufken - George Mason University (United States) [presenting]
Yao Shi - Qingdao University (China)
Wanchunzi Yu - Bridgewater State University (United States)
Abstract: While generalized linear mixed models are useful, optimal design questions for such models are challenging due to the complexity of the information matrices. For longitudinal data, we propose an approximation of the information matrix based on the penalized quasi-likelihood method. We evaluate this approximation for logistic mixed models with time as the single predictor variable. Assuming that the experimenter controls at which time observations are to be made, the approximation is used to identify locally optimal designs based on commonly used optimality criteria. The method can also be used for random block effects models.
