Date of Award

2007

Degree Type

Thesis

Degree Name

Master of Science

Program

Epidemiology and Biostatistics

Supervisor

Dr. John Koval

Second Advisor

Dr. Guangyong Zou

Abstract

The main focus of this thesis is on finding a practical way to impute binary missing values in a data set with arbitrary missing pattern using standard statis tical software. We considered cases where two and three variables with missing values. The method we propose is to use multiple imputation (MI) by Markov Chain Monte Carlo (MCMC) to transfer an arbitrary missing pattern to mono tone missingness, and then apply proper MI for binary data. The simulation study shows that our methods produce more accurate parameter estimates than the rounding method and complete-case analysis. We illustrate our methods with a real data set involving high-school students smoke behavior

Share

COinS
 
 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.