search for




 

Proposed of matching method of imbalanced groups
Journal of the Korean Data & Information Science Society 2018;29:601-8
Published online May 31, 2018
© 2018 Korean Data and Information Science Society.

Imgook Jung1 · Yunhwan Noh2 · Youngseuk Cho3

123Department of Statistics, Pusan National Universit
Correspondence to: Professor, Department of Statistics, Pusan National University, Busan 609-735, Korea. E-mail : Choys@pusan.ac.kr
Received March 19, 2018; Revised May 16, 2018; Accepted May 20, 2018.
This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (http://creativecommons.org/licenses/by-nc/3.0) which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.
Abstract
In this article, we propose a statistical method to find the equivalent group in observational data by using conversion score. In observational study, treatment group and control group are likely to be different groups before research participation. Thus the difference makes rise of selection bias occurrence possibility. In addition, selection bias makes difference between treatment group and control group. One of the methods to overcome the imbalance is propensity score matching (PSM). For case analysis, we use the 2014 traffic accident data.
Keywords : Imbalanced groups, observational study, propensity score matching, sample selection bias.