|
Activity Number:
|
209
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Monday, July 30, 2007 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Section on Survey Research Methods
|
| Abstract - #310120 |
|
Title:
|
Bayesian Multiple Imputation and Maximum Likelihood Methods for Missing Data
|
|
Author(s):
|
Min Sun*+ and Ferry Butar Butar
|
|
Companies:
|
Sam Houston State University and Sam Houston State University
|
|
Address:
|
1701 Bobby K Marks Dr, Huntsville, TX, 77340,
|
|
Keywords:
|
multiple imputation ; Bayesian method ; maximum likelihood ; monte carlo ; boostrap
|
|
Abstract:
|
Bayesian multiple imputation (MI) and Maximum Likelihood (ML) provides a useful strategy for dealing with datasets included missing values. Imputation methods affect the significance of test results and the quality of estimates. In this paper, the general procedures of MI and ML described, which include the normal-based analysis of a multiple imputed dataset. A Monte Carlo simulation is conducted to compare the performances of the methods.
|
