Bayesian Hierarchical Models for Two-Phase Studies

• Activity Number: 468
• Type: Contributed
• Date/Time: Wednesday, August 6, 2014 : 8:30 AM to 10:20 AM
• Sponsor: Section on Statistics in Epidemiology
• Author(s): Michelle Ross*+
• Companies: University of Pennsylvania
• Keywords: Outcome-dependent sampling ; Markov chain Monte Carlo ; Bayesian hierarchical model ; Small area estimation

Abstract

Two-phase study designs are appealing since they allow for the oversampling of rare subpopulations which improves efficiency. In this talk, we describe a Bayesian hierarchical model for two-phase data. Such modeling is particularly appealing in a spatial setting in which random effects are introduced to model between-area variability. In such a situation, one may be interested in estimating regression coefficients or, in the context of small area estimation, in reconstructing the population totals by strata. The surveys that are carried out for small area estimation are often complex in nature and we argue that the two-phase design is a useful approach. The efficiency gains of the two-phase sampling scheme are compared to standard approaches using 2011 birth data from the research triangle area of North Carolina. We show that the proposed method can overcome small sample difficulties and improves on existing techniques.