The determinants of health care expenditure and trends: a semiparametric panel data analysis of OECD countries

Ming Kong, Jiti Gao, Xueyan Zhao

Research output: Chapter in Book/Report/Conference proceedingChapter (Book)Researchpeer-review


This chapter re-examines the determinants of health care expenditure (HCE), using a panel of 32 Organization for Economic Cooperation and Development (OECD) countries from 1990 to 2012. In particular, a panel semiparametric technique (i.e., a partially linear model) is employed, with cross-sectional dependence allowed. Beside the study of coefficients, this chapter investigates the trending functions of HCE. After the common and individual trends of HCE are estimated via semiparametric methods, the authors calibrate them with polynomial specifications, leading to out-of-sample forecasting. The validities of the calibration are tested as well. Contrary to those studies that do not take into account time series properties, our finding suggests that medical care is not a luxury commodity. Other determinants, such as public financing, and the supply of doctors, are all positively related to HCE. Moreover, the calibrated trending models perform well in out-of-sample forecasting.

Original languageEnglish
Title of host publicationEssays in Honor of Cheng Hsiao
EditorsTong Li, M. Hashem Pesaran, dek Terrell
Place of PublicationBingley UK
PublisherEmerald Group Publishing Limited
Number of pages26
ISBN (Electronic)9781789739572, 9781789739596
ISBN (Print)9781789739589
Publication statusPublished - 2020

Publication series

NameAdvances in Econometrics
ISSN (Print)0731-9053


  • Cross-sectional dependence
  • Detection of trend
  • Healthcare expenditure
  • Heterogeneity
  • Parametric calibration
  • Partially linear model

Cite this