Full Text

Turn on search term navigation

© 2025 Zhao et al. This is an open access article distributed under the terms of the Creative Commons Attribution License: http://creativecommons.org/licenses/by/4.0/ (the “License”), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.

Abstract

Modeling medical costs is a crucial task in health economics, especially when high-dimensional covariates and nonlinear effects are present. In this study, we propose a partially nonlinear index model (PNIM) that integrates partially sufficient dimension reduction with a rapid instrumental variable pilot estimation method. Through simulations, we demonstrate that the proposed model excels at capturing significant nonlinear relationships. When applying the model to the Medical Expenditure Panel Survey (MEPS) dataset, we identify important nonlinear age effects on medical costs and highlight key factors such as hospitalization, cardiovascular diseases, and supplemental insurance coverage. These findings provide valuable insights for healthcare policy, including targeted interventions for specific age groups and enhanced management of chronic conditions. Overall, the proposed method offers a flexible and computationally efficient framework for analyzing complex medical cost data, with broad applicability in health economics.

Details

Title
Sufficient dimension reduction on partially nonlinear index models with applications to medical costs analysis
Author
Zhao, Xiaobing; Xia, Yufeng; Xu, Xuan  VIAFID ORCID Logo 
First page
e0321796
Section
Research Article
Publication year
2025
Publication date
May 2025
Publisher
Public Library of Science
e-ISSN
19326203
Source type
Scholarly Journal
Language of publication
English
ProQuest document ID
3203838028
Copyright
© 2025 Zhao et al. This is an open access article distributed under the terms of the Creative Commons Attribution License: http://creativecommons.org/licenses/by/4.0/ (the “License”), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.