Modelling health expenditure at the household level in Greece
- 27 November 2008
- journal article
- Published by Springer Nature in The European Journal of Health Economics
- Vol. 10 (3) , 329-336
Abstract
Health expenditure data are known to be afflicted by restricted range, zero values, skewness and kurtosis. Several methods for modelling such data have been suggested in the literature to cope with these problems. This paper compares the performance of several alternative estimators, including two-part models and generalised linear models. The dependent variable is household expenditure on health care in Greece, a country where out-of-pocket health expenditure is higher than anywhere else in the European Union, whether as a proportion of GDP, as a share of all health spending, or in per capita terms. To facilitate comparison of model performance, household health expenditure is examined in two different specifications: expenditure on all health care (where zero values are rare) and expenditure on hospital services alone (where zero values are common). In the case of expenditure on all health care, three of the estimators performed almost equally well in terms of three alternative model performance indicators: a modified two-part model with non-linear least squares in the second part, a constant-variance generalised linear model and a variance-proportional-to-mean generalised linear model. In the case of expenditure on hospital services, the constant-variance generalised linear model out-performed the rest. The findings suggest that no estimator is best under all circumstances, while most alternative estimators are likely to produce relatively similar results. The paper concludes by discussing implications for further research.Keywords
This publication has 16 references indexed in Scilit:
- A robust approach for skewed and heavy-tailed outcomes in the analysis of health care expendituresJournal of Health Economics, 2006
- Too much ado about two-part models and transformation?Journal of Health Economics, 2004
- Comparing alternative models: log vs Cox proportional hazard?Health Economics, 2003
- The structure of demand for health care: latent class versus two-part modelsJournal of Health Economics, 2002
- Estimating log models: to transform or not to transform?Journal of Health Economics, 2001
- METHODS FOR ANALYZING HEALTH CARE UTILIZATION AND COSTSAnnual Review of Public Health, 1999
- Modeling risk using generalized linear modelsJournal of Health Economics, 1999
- The logged dependent variable, heteroscedasticity, and the retransformation problemJournal of Health Economics, 1998
- Smearing Estimate: A Nonparametric Retransformation MethodJournal of the American Statistical Association, 1983
- A Comparison of Alternative Models for the Demand for Medical CareJournal of Business & Economic Statistics, 1983