A0551
Title: A Bayesian approach to process optimization on data with multi-stratum structure
Authors: Po Yang - University of Manitoba (Canada) [presenting]
Abstract: Multistratum design arises naturally in industrial experiments due to the inconvenient and impractical complete randomization. Most research has concentrated on finding optimal multi-stratum designs with high parameter estimation efficiencies. Accounting for the model uncertainty, the Bayesian model averaging method and predictive approach are applied to investigate the optimization problem for data with a multi-stratum structure. With the posterior probabilities of models as weights, the weighted average of the predictive densities of the response overall potential models are considered. The goal of the optimization is to identify the values of the factors that result in a maximum probability of a response in a given range. The method is illustrated with two examples.
