Sabine K. Schnabel
Paul H.C. Eilers

http://www.demographic-research.org/volumes/vol21/5/

doi:10.4054/DemRes.2009.21.5

	Click the icon to view and/or download the PDF file. Once you are in the PDF file, use your browser back button to return to this page.

Abstract
The wealth of a country is assumed to have a strong non-linear influence on the life expectancy of its inhabitants. We follow up on research by Preston and study the relationship with gross domestic product. Smooth curves for the average but also for (upper) frontiers are constructed by a combination of least asymmetrically weighted squares and P-splines. Guidelines are given for optimizing the amount of smoothing and the definition of frontiers. The model is applied to a large set of countries in different years. It is also used to estimate life expectancy performance for individual countries and to show how it changed over time.

Author's affiliation
Sabine K. Schnabel
Biometris, Wageningen University, Netherlands
Paul H.C. Eilers
Erasmus Medical Center, Rotterdam, Netherlands

Keywords
frontier estimation, gross domestic product, least asymmetrically weighted squares, life expectancy, production frontier, smoothing

Word count (Main text)
4940

Most recent similar articles in Demographic Research

	[22-5] Life expectancy is the death-weighted average of the reciprocal of the survival-specific force of mortality (life expectancy)
	[21-29] Survival as a Function of Life Expectancy (life expectancy)
	[20-19] Trends in healthy life expectancy in Japan: 1986 - 2004 (life expectancy)
	[19-35] An integrated approach to cause-of-death analysis: cause-deleted life tables and decompositions of life expectancy (life expectancy)
	[18-14] Constant global population with demographic heterogeneity (life expectancy)

[ Back to previous page ]