WITHDRAWN: Hierarchical Bayesian Analysis of Organ Weight Toxicity Data Across Multiple Rodent Studies

• Activity Number: 289 - Recent Advances in Mathematical Statistics and Probability
• Type: Contributed
• Date/Time: Wednesday, August 11, 2021 : 1:30 PM to 3:20 PM
• Sponsor: IMS
• Author(s): GARY LARSON and Jeffrey Krause and Guanhua Xie and Shawn Harris and Sandra McBride and Keith Shockley
• Companies: DLH CORPORATION and DLH CORPORATION and DLH CORPORATION and DLH CORPORATION and DLH CORPORATION and National Institute of Environmental Health Sciences
• Keywords: toxicology; hierarchical Bayesian model; hyperprior; organ weight data; relative organ weight

Abstract

When studying a chemical’s toxicity, researchers collect experimental data on organ weight changes in exposed animals. Organ weight changes can indicate adverse effects in response to the exposure. However, organ weights are correlated with body weights, which also may be directly affected by exposure. To properly interpret organ weight changes and control for the dependence on body weight, the organ-to-body weight ratio (relative organ weight) is traditionally used. Characteristics of this approach were explored by a recently published Bayesian causal method, using data from a National Toxicology Program (NTP) study. In this presentation we expand the Bayesian causal model with hyperpriors, applying the approach to multiple NTP studies simultaneously. By borrowing information across studies with identical species and similar experimental setups, the expanded model provides new insights into the variability of body/organ weight correlations across NTP studies.