search for




 

Analysis of health-related quality of life using Beta regression
Journal of the Korean Data & Information Science Society 2017;28:547-57
Published online May 31, 2017
© 2017 Korean Data & Information Science Society.

Eun Jin Jang1

1Department of Information Statistics, Andong National University
Correspondence to: Eun Jin Jang
Assistant professor, Department of Information Statistics, Andong National University, Gyeongbuk 36729, Republic of Korea. E-mail: ejjang@anu.ac.kr
Received April 18, 2017; Revised May 14, 2017; Accepted May 17, 2017.
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
The health-related quality of life data are commonly skewed and bounded with spike at the perfect health status, and the variance tended to be heteroscedastic. In this study, we have developed a prediction model for EQ-5D using linear regression model, beta regression model, and extended beta regression model with mean and precision submodel, and also compared the predictive accuracy. The extended beta regression model allows to model skewness and differences in dispersion related to covariates. Although the extended beta regression model has higher prediction accuracy than the linear regression model, the overlapped confidence intervals suggested that the extended beta regression model was superior to the linear regression model. However, the expended beta regression model could explain the heteroscedasticity and predict within the bounded range. Therefore, the expended beta regression model are appropriate for fitting the health-related quality of life data such as EQ-5D.
Keywords : Beta regression, health-related quality of life, heteroskedasticity, Korea health panel survey.


KDISS e-Submission go

May 2017, 28 (3)