FRIDAY, November 18, 2005
Time: 1:00 - 2:00 PM
E & CS Building Room 1202 (First Floor Auditorium)

Title: Comparison of Designs For Multivariate Generalized Linear Models

Siulu Mukhopadhyay
Department of Statistics
University of Florida

The purpose of this talk is to discuss response surface designs for multivariate generalized linear models (GLMs). Such models are considered whenever several response variables can be measured for each setting of a group of control variables, and the response variables are adequately represented by GLMs. The mean-squared error of prediction (MSEP) matrix is used to assess the quality of prediction associated with a given design. The MSEP incorporates both the prediction variance and the prediction bias, which results from using maximum likelihood estimates of the parameters of the fitted linear predictor. For a given design, quantiles of a scalar-valued function of the MSEP are obtained within a certain region of interest. The quantiles depend on the unknown parameters of the linear predictor. The dispersion of these quantiles over the space of the unknown parameters is determined resulting in the so-called quantile dispersion graphs. A numerical example based on a bivariate binary distribution is presented to illustrate the proposed methodology. We study two respiratory ailments of working coalminers who were smokers without radiological evidence of pneumoconiosis, aged between 20 and 64 at the time of examination. Each respondent was classified as suffering from breathlessness or wheeze.