Detecting Pattern in Biological Stressor Response Relationships Using Model-based Cluster Analysis

• Activity Number: 298
• Type: Topic Contributed
• Date/Time: Wednesday, August 11, 2004 : 8:30 AM to 10:20 AM
• Sponsor: Section on Bayesian Statistical Science
• Author(s): Ilya A. Lipkovich*+
• Companies: Eli Lilly and Company
• Keywords: water quality ; regression ; Bayesian methods ; Markov chain Monte Carlo

Abstract

Environmental monitoring of aquatic systems is needed to estimate the quality of the systems, to evaluate standards and to study stressor-response relationships. The monitoring program focuses on the collection of biological, chemical, and physical measures of the system. An important concern is the effect of chemical and physical stressors on the biological community. From a management perspective, interest is on what factors affect the biological community and how the relationship changes within the state. The focus of this paper is on the use of cluster analysis as a tool for finding relationships between a single biological response and environmental stressors. The approach to cluster analysis is based on the use a model-based analysis using a penalized classification likelihood. The mean parameter depends on the relationship as well as the cluster. This approach allows for simultaneous development of regression models and clustering of the regression models. The implementation of the approach is based on Markov chain Monte Carlo Model Comparison. This method is applied to the analysis of a dataset describing stressors/response relationship in one of the Ohio eco-regions.