|
Activity Number:
|
332
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Tuesday, July 31, 2007 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Biometrics Section
|
| Abstract - #310306 |
|
Title:
|
A Bayesian Analysis of Spatially Correlated Binary Data with Applications in Dental Research
|
|
Author(s):
|
Yanwei Zhang*+ and David Todem and R. V. Ramamoorthi
|
|
Companies:
|
Michigan State University and Michigan State University and Michigan State University
|
|
Address:
|
Division of Biostatistics, East Lansing, MI, 48824,
|
|
Keywords:
|
Spatial Correlation ; Multilevel Nested Co-dependency Structure ; Finite Mixture Model ; Undirected Graphical Model ; Bayesian Hypothesis Testing
|
|
Abstract:
|
Analysis of dental caries is traditionally based on DMFS and DMFT scores. Although this approach has aided our understanding of the pattern of dental caries, there are still some fundamental unanswered questions. As an example, it is believed among dentists that there are spatial symmetries in the mouth with respect to caries, but this has never been shown in a statistical sense. An answer to this question requires the analysis to be performed at the tooth level. In this paper, we formulate a finite Bayesian mixture model coupled with an undirected graphical approach to accommodate the nested co-dependency structure of dental data. The spatial symmetry of the development of dental caries in the mouth is assessed using the Bayesian principle. Data from a cross-sectional survey are used to illustrate the method.
|
