Backtesting Longevity Models: An International Perspective
Details
Serval ID
serval:BIB_CC017C7E8D13
Type
Report: a report published by a school or other institution, usually numbered within a series.
Publication sub-type
Working paper: Working papers contain results presented by the author. Working papers aim to stimulate discussions between scientists with interested parties, they can also be the basis to publish articles in specialized journals
Collection
Publications
Institution
Title
Backtesting Longevity Models: An International Perspective
Institution details
Cronos Finance
Address
Pully, Switzerland
Issued date
2015
Language
english
Abstract
The work proposes a backtesting analysis in comparison between the Lee-Carter and the Cairns-Blake-Dowd mortality models, employing Italian data. The mortality data come from the Italian National Statistics Institute (ISTAT) database and span the period 1975-2014, over which we computed back-projections evaluating the performances of the models in comparisons with real data. We propose three different backtest approaches, evaluating the goodness of short-run forecast versus long-run ones. We find that both models were not able to capture the improving shock on the mortality observed for the male population on the analyzed period.
Moreover, the results suggest that CBD forecast are reliable prevalently for ages above 75, and that LC forecast are basically more accurate for this data.
Moreover, the results suggest that CBD forecast are reliable prevalently for ages above 75, and that LC forecast are basically more accurate for this data.
Keywords
lee-carter, cairns-blake-dowd, mortality models, backtesting
Create date
19/10/2017 11:08
Last modification date
21/08/2019 6:15