Activity Number:
|
294
|
Type:
|
Contributed
|
Date/Time:
|
Tuesday, July 31, 2007 : 10:30 AM to 12:20 PM
|
Sponsor:
|
Section on Bayesian Statistical Science
|
Abstract - #310221 |
Title:
|
Bayesian Analysis of Correlated Proportions (Matched-Pair Data) in 2 x 2 Tables with Incompletely Classified Data: Bayesian Extension of McNemar's Test to Missing Data
|
Author(s):
|
Yan Lin*+ and Stuart R. Lipsitz and Debajyoti Sinha and Scott Regenbogen and Caprice Greenberg
|
Companies:
|
The University of Texas M.D. Anderson Cancer Center and Brigham and Women's Hospital and Medical University of South and Harvard School of Public Health and Brigham and Women's Hospital
|
Address:
|
1515 Holcombe Blvd Unit 447, Houston, TX, 77030,
|
Keywords:
|
Dirichlet prior ; Gibbs sampler ; Ignorable missing data ; 2 x 2 table
|
Abstract:
|
Altham (1971) proposed a Bayesian analysis of a 2 x 2 contingency table formed from matched pairs. Using the same Bayesian perspective, we develop an extension of Altham's Bayesian methods to a 2 x 2 table from matched pairs with missing data and under an ignorable missing data mechanism. In particular, we develop a Bayesian p-value similar to the p-value from McNemar's test, which, unlike McNemar's test, incorporates the missing data into the analysis. We use a simulation study to explore the power and Type I error rate of our proposed test statistic.
|