Eliciting Informative Priors for Bayesian Hurdle Models

• Activity Number: 414
• Type: Contributed
• Date/Time: Tuesday, August 5, 2014 : 2:00 PM to 3:50 PM
• Sponsor: Section on Bayesian Statistical Science
• Author(s): Joyce Cheng*+ and David Kahle and John W. Seaman
• Companies: Baylor University and Baylor University and Baylor University
• Keywords: hurdle models ; Bayesian ; informative priors

Abstract

Hurdle models are often presented as an alternative to zero-inflated models for count data with excess zeros. Hurdle models consist of two parts: a binary model indicating a positive response (the "hurdle") and a zero-truncated count model. One or both parts of the model can be dependent on covariates, which are often the same due to the nature of the problem. Many of the Bayesian hurdle models encountered in the literature fail to incorporate expert opinion into the prior structure. In this work, we consider how prior information can be elicited from experts and incorporated into the prior structure of a hurdle model with shared covariates using conditional means priors. More specifically, we propose a prior structure that takes advantage of the inherent functional relationship between the two parts of the model. A hypothetical sleep disorder study is then analyzed to demonstrate the potential gains of the approach.