Extending the Lee-Carter model: a three-way decomposition. (English) Zbl 1277.62260

Summary: In this paper, we focus on a multi-dimensional data analysis approach to the Lee-Carter (LC) model of mortality trends. In particular, we extend the bilinear LC model and specify a new model based on a three-way structure, which incorporates a further component in the decomposition of the log-mortality rates. A multi-way component analysis is performed using the Tucker3 model. The suggested methodology allows us to obtain combined estimates for the three modes: (1) time, (2) age groups and (3) different populations. From the results obtained by the Tucker3 decomposition, we can jointly compare, in both a numerical and graphical way, the relationships among all three modes and obtain a time-series component as a leading indicator of the mortality trend for a group of populations. Further, we carry out a correlation analysis of the estimated trends in order to assess the reliability of the results of the three-way decomposition. The model’s goodness of fit is assessed using an analysis of the residuals. Finally, we discuss how the synthesised mortality index can be used to build concise projected life tables for a group of populations. An application which compares 10 European countries is used to illustrate the approach and provide a deeper insight into the model and its implementation.


62P05 Applications of statistics to actuarial sciences and financial mathematics
62-04 Software, source code, etc. for problems pertaining to statistics
62H25 Factor analysis and principal components; correspondence analysis
62M10 Time series, auto-correlation, regression, etc. in statistics (GARCH)
91B30 Risk theory, insurance (MSC2010)


Full Text: DOI


[1] DOI: 10.1016/S0167-6687(02)00185-3 · Zbl 1074.62524
[2] Carroll J. D., Proceedings of the 76th Annual Convention of the American Psychological Association 3 pp 227– (1968)
[3] Carter , L. & Prkawetz , A. 2001 . Examining structural shifts in mortality using the Lee-Carter method .MPIDRwork paper. Rostock 2002, 16 p. (wp-2001-007). Available athttp://www.demogr.mpg.de/Papers/working/wp-2001-007.pdf
[4] DOI: 10.1007/BF02288367 · JFM 62.1075.02
[5] DOI: 10.1016/0167-9473(94)90135-X · Zbl 0825.62517
[6] DOI: 10.1007/978-88-470-0704-8_17
[7] DOI: 10.1111/j.1539-6924.2005.00671.x
[8] DOI: 10.1016/j.insmatheco.2008.10.008 · Zbl 1156.91394
[9] DOI: 10.1037/h0071325
[10] DOI: 10.1002/1099-128X(200005/06)14:3<151::AID-CEM585>3.0.CO;2-G
[11] DOI: 10.1348/000711003321645386
[12] DOI: 10.1037/1082-989X.6.1.84
[13] Kroonenberg P. M., Three mode principal component analysis. Theory and applications (1983) · Zbl 0513.62059
[14] DOI: 10.1007/BF02293599 · Zbl 0431.62035
[15] DOI: 10.2307/2290201
[16] DOI: 10.1111/1467-9876.00393 · Zbl 1111.62359
[17] DOI: 10.1016/S0167-6687(03)00118-5 · Zbl 1025.62041
[18] DOI: 10.1016/j.insmatheco.2009.07.006 · Zbl 1231.91195
[19] Tabeau E., Forecasting mortality in developed countries (2001)
[20] DOI: 10.1348/000711000159132
[21] DOI: 10.1007/BF02289464
[22] Tukey J. W., Exploratory data analysis (1977) · Zbl 0409.62003
[23] DOI: 10.1038/35015561
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.