A Hierarchical Bayesian Model for Environmental Correlated Count Processes with Application to Fisheries Habitat Management

• Activity Number: 138
• Type: Contributed
• Date/Time: Monday, August 2, 2010 : 8:30 AM to 10:20 AM
• Sponsor: Section on Statistics and the Environment
• Author(s): Ali Arab*+ and Scott Holan and Christopher Wikle and Mark Wildhaber
• Companies: Georgetown University and University of Missouri and University of Missouri and U.S. Geological Survey
• Keywords: Hierarchicak models ; Bayesian inference ; Ecology ; Environment ; Correlated Counts ; Fisheries

Abstract

Hierarchical Bayesian modeling approaches provide a flexible and effective tool for modeling problems related to habitat management in fisheries. Intensive management of the Missouri River such as impoundments, flow regulations, and channelization of the river for purposes of navigation, flood control, and power generation has resulted in dramatic physical changes to the river corridor, eliminating many acres of habitat for native fish. There have been several studies conducted by the U.S. Geological Survey (USGS) to evaluate the impact of such alterations and modifications of the river basin on the recruitment, growth, and relative abundance of selected benthic fish species. In this work, the analysis of zero-inflated multi-species catch data obtained by multiple gears using a semiparametric hierarchical Bayesian bivariate Poisson model is discussed.