A Diversity Index for Model Selection in the Estimation of Benchmark and Infectious Doses via Frequentist Model Averaging

• Activity Number: 79
• Type: Contributed
• Date/Time: Sunday, August 4, 2013 : 4:00 PM to 5:50 PM
• Sponsor: Section on Risk Analysis
• Author(s): Steven Kim*+ and Ralph Kodell and Hojin Moon
• Companies: University of California, Irvine and University of Arkansas for Medical Sciences and California State University, Long Beach
• Keywords: Data uncertainty ; Model uncertainty ; Model averaging ; Kullback-Leibler divergence

Abstract

In chemical and microbial risk assessments, risk assessors fit dose-response models to high-dose data and extrapolate downward to risk levels in the range of 1% to 10%. Although multiple dose-response models may be able to fit the data adequately in the experimental range, the estimated effective dose corresponding to an extremely small risk can be substantially different from model to model. In this respect, using model averaging is more appropriate than relying on any single dose-response model in the calculation of a point estimate and a lower confidence limit for an effective dose. In model averaging, accounting for both data uncertainty and model uncertainty is crucial, but proper variance estimation is not guaranteed simply by increasing the number of models in a model space. A plausible set of models in model averaging can be characterized by good fits to the data and diversity surrounding the truth. We propose a diversity index for model selection which balances between goodness-of-fit and divergence among a set of parsimonious models. Tuning parameters in the diversity index control the size of the model space for model averaging.