SciELO - Scientific Electronic Library Online

vol.9 issue1Years of life lost from cancer: trends and differentials by sex in Córdoba, Argentina, 2000-2009 periodInclusion, basic pensions and (in)equality: the distribution of economic protection in old age in four Latin American countries author indexsubject indexarticles search
Home Pagealphabetic serial listing  

Services on Demand




  • Have no cited articlesCited by SciELO

Related links

  • Have no similar articlesSimilars in SciELO



Print version ISSN 1852-4418On-line version ISSN 1852-4222


ANDREOZZI, Lucía  and  VENTRONI, Nora. Clife expectancy's probabilistic forecasts for Rosario city, Argentina. SaberEs [online]. 2017, vol.9, n.1, pp.47-67. ISSN 1852-4418.

Life expectancy at birth is one of the most useful indices for measuring the overall level of mortality and estimates the level of mortality more accurately than the crude mortality rate because it is independent of the age structure of the population. It also allows to compare the levels of mortality for different populations in different historical moments. Probabilistic forecasting models generate age-specific mortality rates for future periods, and from these results it is possible to derive forecasts of life expectancy at birth and their corresponding confidence intervals. In this paper two models are applied; the forerunner of probabilistic models of mortality prediction: the Lee and Carter model (1992) and another one, the last proposed in the area: the functional data model developed by Hyndman and Ullah (2008). Both models predict mortality, and allow, through living tables based on mortality forecasts, to derive life expectancy at birth. The application is made to mortality data of Rosario City, from 1980 to 2015, to obtain specific forecasts and intervals for life expectancy at birth with their respective intervals.

Keywords : Functional data; Lee-Carter model; Forecast interval.

        · abstract in Spanish     · text in Spanish     · Spanish ( pdf )


Creative Commons License All the contents of this journal, except where otherwise noted, is licensed under a Creative Commons Attribution License