Identifiability issues of age-period and age-period-cohort models of the Lee-Carter type. (English) Zbl 1394.91188

Summary: The predominant way of modelling mortality rates is the Lee-Carter model and its many extensions. The Lee-Carter model and its many extensions use a latent process to forecast. These models are estimated using a two-step procedure that causes an inconsistent view on the latent variable. This paper considers identifiability issues of these models from a perspective that acknowledges the latent variable as a stochastic process from the beginning. We call this perspective the plug-in age-period or plug-in age-period-cohort model. Defining a parameter vector that includes the underlying parameters of this process rather than its realizations, we investigate whether the expected values and covariances of the plug-in Lee-Carter models are identifiable. It will be seen, for example, that even if in both steps of the estimation procedure we have identifiability in a certain sense it does not necessarily carry over to the plug-in models.


91B30 Risk theory, insurance (MSC2010)
91D20 Mathematical geography and demography
62P05 Applications of statistics to actuarial sciences and financial mathematics
Full Text: DOI arXiv


[1] Anderson, T. W.; Rubin, H., Statistical inference in factor analysis, in: J. Neyman (ed.), in: Proceedings of the Third Berkeley Symposium on Mathematical Statistics and Probability, Vol. V, 114-150, (1956), University of California Press Berkeley
[2] Booth, H., Demographic forecasting: 1908 to 2005 in review, Int. J. Forecast., 22, 547-581, (2006)
[3] Booth, H.; Tickle, L., Mortality modelling and forecasting: a review of methods, Ann. Actuar. Sci., 3, 3-43, (2008)
[4] Bowers, N. L.; Gerber, H. U.; Hickman, J. C.; Jones, D. A.; Nesbitt, C. J., Actuarial Mathematics, (1997), Society of Actuaries Schaumburg
[5] Brockwell, P. J.; Davis, R. A., Time Series: Theory and Methods, (2006), Springer Science Business Media New York
[6] Brouhns, N.; Denuit, M.; van Keilegom, I., Bootstrapping the Poisson log-bilinear model for mortality forecasting, Scand. Actuar. J., 3, 212-224, (2005) · Zbl 1092.91038
[7] Cairns, A. J.G.; Blake, D.; Dawson, P.; Dowd, K., Pricing the risk on longevity bonds, Life Pensions, 41-44, (2005), October
[8] Cairns, A. J.G.; Blake, D.; Dowd, K., Modelling and management of mortality risk: a review, Scand. Actuar. J., 2008, 79-113, (2008) · Zbl 1224.91048
[9] Cairns, A. J.G.; Blake, D.; Dowd, K.; Coughlan, G. D.; Epstein, D.; Ong, A.; Balevich, I., A quantitative comparison of stochastic mortality models using data from england and wales and the united states, N. Am. Actuar. J., 13, 1-35, (2009)
[10] Coelho, E.; Nunes, L., Forecasting mortality in the event of a structural change, J. R. Stat. Soc. Ser. A, 174, 713-736, (2011)
[11] Currie, I. D., On Fitting generalized linear and non-linear models of mortality, Scand. Actuar. J., 2016, 356-383, (2016) · Zbl 1401.91123
[12] De Jong, P.; Tickle, L., Extending Lee-Carter mortality forecasting, Math. Popul. Stud., 13, 1-18, (2006) · Zbl 1151.91742
[13] Fung, M. C.; Peters, G. W.; Shevchenko, P. V., A unified approach to mortality modelling using state-space framework: characterisation, identification, estimation and forecasting, Ann. Actuar. Sci., (2016)
[14] Girosi, F., King, G., (2007). Understanding the Lee-Carter Mortality Forecasting Method. Copy at http://j.mp/lTXlGe
[15] Haberman, S.; Renshaw, A., Mortality, longevity and experiments with the Lee-Carter model, Lifetime Data Anal., 14, 286-315, (2008) · Zbl 1356.62205
[16] Haberman, S.; Renshaw, A., On age-period-cohort parametric mortality rate projections, Insurance Math. Econom., 45, 255-270, (2009) · Zbl 1231.91195
[17] Haberman, S.; Renshaw, A., A comparative study of parametric mortality projection models, Insurance Math. Econom., 48, 35-55, (2011)
[18] Hald, A., A History of Probability and Statistics and their Applications before 1750, (2003), John Wiley & Sons, Inc. Hoboken, New Jersey
[19] Heaton, C.; Solo, V., Identification of causal factor models of stationary time series, Econom. J., 7, 618-627, (2004) · Zbl 1114.91351
[20] Hunt, A.; Villegas, A. M., Robustness and convergence in the Lee-Carter model with cohort effects, Insurance Math. Econom., 64, 186-202, (2015) · Zbl 1348.62241
[21] Kuang, D.; Nielsen, B.; Nielsen, J.-P., Forecasting with the age-period-cohort model and the extended chain-ladder model, Biometrika, 95, 987-991, (2008) · Zbl 1437.62516
[22] Kuang, D.; Nielsen, B.; Nielsen, J.-P., Identification of the age-period-cohort model and the extended chain-ladder model, Biometrika, 95, 979-986, (2008) · Zbl 1437.62515
[23] Kuang, D.; Nielsen, B.; Nielsen, J.-P., Forecasting in an extended chain-ladder-type model, J. Risk Insur., 78, 345-359, (2011)
[24] Lee, R. D.; Carter, L. R., Modeling and forecasting U. S. mortality, J. Amer. Statist. Assoc., 87, 659-671, (1992) · Zbl 1351.62186
[25] Leng, X.; Peng, L., Inference pitfalls in Lee-Carter model for forecasting mortality, Insurance Math. Econom., 70, 58-65, (2016) · Zbl 1371.91098
[26] Nielsen, B.; Nielsen, J.-P., Identification and forecasting in mortality models, Sci. World J., (2014), 2014, Article ID 347043, http://dx.doi.org/10.1155/2014/347043 · Zbl 1328.62575
[27] Rencher, A. C., Methods of Multivariate Analysis, (2002), John Wiley & Sons, Inc. New York · Zbl 0995.62056
[28] Renshaw, A. E.; Haberman, S., A cohort-based extension to the Lee-Carter model for mortality reduction factors, Insurance Math. Econom., 38, 556-570, (2006) · Zbl 1168.91418
[29] Yang, B.; Li, J.; Balasooriya, U., Cohort extensions of the Poisson common factor model for modelling both genders jointly, Scand. Actuar. J., 2016, 2, 93-112, (2016) · Zbl 1401.91203
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.