Odds Ratio Estimation in Rare Data by Empirical Bayes Method

Authors

  • Kobkun Raweesawat Department of Applied Statistics, Faculty of Applied Science, King Mongkut’s University of Technology North Bangkok, Bangkok, Thailand
  • Yupaporn Areepong Department of Applied Statistics, Faculty of Applied Science, King Mongkut’s University of Technology North Bangkok, Bangkok, Thailand
  • Saowanit Sukparungsee Department of Applied Statistics, Faculty of Applied Science, King Mongkut’s University of Technology North Bangkok, Bangkok, Thailand
  • Katechan Jampachaisri Department of Mathematics, Faculty of Science, Naresuan University, Phitsanuloke, Thailand

Keywords:

Odds ratio, empirical Bayes, Poisson distribution, modified maximum likelihood estimator

Abstract

The Empirical Bayes estimator (EB) of odds ratio in rare data is considered in this paper. The proposed estimate of odds ratio based on EB in Poisson distribution to approximate binomial distribution is then compared to conventional method, modified maximum likelihood estimator (MMLE), using the Estimated Relative Error (ERE) as a criterion of comparison. The result indicated that the EB estimator is a more efficient method than MMLE.

Downloads

Published

2017-07-08

How to Cite

Raweesawat, K., Areepong, Y., Sukparungsee, S., & Jampachaisri, K. (2017). Odds Ratio Estimation in Rare Data by Empirical Bayes Method. Thailand Statistician, 15(2), 149–156. Retrieved from https://ph02.tci-thaijo.org/index.php/thaistat/article/view/92198

Issue

Section

Articles