Assessing local model adequacy in Bayesian hierarchical models using the partitioned deviance information criterion

  • Authors:

  • David C. Wheeler;DeMarc A. Hickson;Lance A. Waller

  • Affiliations:

  • National Cancer Institute, 6120 Executive Boulevard, Bethesda, MD 20892, United States;University of Mississippi Medical Center, School of Medicine, Department of Medicine, 2500 North State Street, Jackson, MS 39213, United States;Emory University, Rollins School of Public Health, Department of Biostatistics, 1518 Clifton Road, Atlanta, GA 30322, United States

  • Venue:
  • Computational Statistics & Data Analysis
  • Year:
  • 2010

Quantified Score

Hi-index 0.03

Visualization

Abstract

Many diagnostic tools and goodness-of-fit measures, such as the Akaike information criterion (AIC) and the Bayesian deviance information criterion (DIC), are available to evaluate the overall adequacy of linear regression models. In addition, visually assessing adequacy in models has become an essential part of any regression analysis. In this paper, we focus on a spatial consideration of the local DIC measure for model selection and goodness-of-fit evaluation. We use a partitioning of the DIC into the local DIC, leverage, and deviance residuals to assess the local model fit and influence for both individual observations and groups of observations in a Bayesian framework. We use visualization of the local DIC and differences in local DIC between models to assist in model selection and to visualize the global and local impacts of adding covariates or model parameters. We demonstrate the utility of the local DIC in assessing model adequacy using HIV prevalence data from pregnant women in the Butare province of Rwanda during the period 1989-1993 using a range of linear model specifications, from global effects only to spatially varying coefficient models, and a set of covariates related to sexual behavior. Results of applying the diagnostic visualization approach include more refined model selection and greater understanding of the models as applied to the data.