STA/BST 290 Seminar Series
Tuesday, May 19, 2015, 4:10pm, MSB 1147 (Colloquium Room)
Refreshments at 3:30pm in MSB 4110 (Statistics Lounge)
Speaker: Abhyuday Mandal
(University of Georgia, Athens)
Title: Optimal Design of Experiments for Generalized Linear Models
Abstract: Generalized linear models have been used widely for modeling the mean response both for discrete and continuous random variables with an emphasis on categorical response. Optimal allocation of runs in replicated design of experiments is an intellectually challenging and important practical problem. In this research we address this question in the context of several optimality criteria, namely D-optimality, EW-optimality and Bayesian optimality. In the absence of the theoretical results on the optimal allocation of replicates for binary, Poisson and multinomial responses, the choice of uniform design is popular in practice. Regular fractional factorial designs are often used in practice. We will show that these popular designs, which are known to best for normal responses, are often not optimal for binomial, Poission and multinomial cases.