Models for Health Care

Andrew M. Jones

in The Oxford Handbook of Economic Forecasting

Published in print July 2011 | ISBN: 9780195398649
Published online September 2012 | | DOI:

Series: Oxford Handbooks

 Models for Health Care

More Like This

Show all results sharing these subjects:

  • Economics
  • Econometric and Statistical Methods and Methodology: General


Show Summary Details


This article, which provides an outline of the methods that are typically used to model individual health care costs, reviews the literature on the comparative performance of the methods, especially in the context of forecasting individual health care costs, and concludes with an empirical case study. It is organized as follows. Section 2 begins with linear regression on the level of costs and on transformations of costs. Section 3 moves on to nonlinear regressions that are specified in terms of an exponential conditional mean. Many recent studies of nonlinear specifications are embedded within the generalized linear model (GLM) framework. The language of the GLM approach is commonplace in the statistics literature, but is less used in econometrics and is outlined in Section 4. Recent research has seen the development of more flexible parametric and semiparametric approaches, and some of the key methods are described in Section 5. Section 6 reviews evidence on the comparative performance of methods that are most commonly used to model costs and for some of the recent methodological innovations. This is reinforced in Section 7, which presents an illustrative application of the methods with data from the US Medical Expenditure Panel Study. Section 8 suggests some further reading.

Keywords: health care cost; nonlinear regression; generalized linear model; cost modeling

Article.  11874 words. 

Subjects: Economics ; Econometric and Statistical Methods and Methodology: General

Full text: subscription required

How to subscribe Recommend to my Librarian

Buy this work at Oxford University Press »

Users without a subscription are not able to see the full content. Please, subscribe or login to access all content.