Combining environmental information via hierarchical modeling: an example using mutagenic potencies

Mutagenesis assays of toxic environmental agents often provide only a single snapshot of the agent's potential risk, leading to inferences on a possibly isolated phenomenon. Hierarchical models can enhance inferences on environmental agents and obtain more global perspectives on the potential risk. We investigate the use of such models to combine information across environmental studies. We emphasize combination of potency estimates from bioassays used for environmental hazard identification and risk assessment. The models and methods illustrate hierarchical Bayesian techniques to estimate the parameters and make inferences on the unknown potency values. Copyright (C) 2003 John Wiley Sons, Ltd.