Abstract
Already a 1% improvement to the overall forecast accuracy of mortality rates, may lead to the significant decrease of insurers costs. In practice, Lee-Carter model is widely used for forecasting the mortality rates. Within this study, we combine the traditional Lee-Carter model with the recent advances in the weighted model averaging. For this purpose, first, the training database of template predictive models is constructed for the mortality data and processed with similarity measures, and secondly, competitive predictive models are averaged to produce forecasts. The main innovation of the proposed approach is reflecting the uncertainty related to the shortness (e.g., 14 observations) of available data by the incorporation of multiple predictive models. The performance of the proposed approach is illustrated with experiments for the Human Mortality Database. We analyzed time series datasets for women and men aged 0–100 years from 10 countries in the Central and Eastern Europe. The presented numerical results seem very promising and show that the proposed approach is highly competitive with the state-of-the-art models. It outperforms benchmarks especially when forecasting long periods (6–10 years ahead).
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
We can distinguish high mortality countries from low mortality countries with life expectancy at birth [United Nations, Department of Economic and Social Affairs, Population Division (2013). World Mortality Report 2013 (United Nations publication)]. This indicator for Euro Area overtakes 82, while for Central Europe and the Baltics equals 77 [The World Bank 2015].
- 2.
Datasets are available for download from https://www.mortality.org.
- 3.
Some authors calculate prediction errors based on the model’s variable \(\ln (m_ {x, t})\). It is worth pointing out that this approach does not always generate the same conclusions (the results are not equivalent). From a practical point of view we are interested in the central death rate. The LC model is just a estimation tool. Therefore, we compute errors comparing the estimated values to the central death rate.
- 4.
According to MAE relative differences.
References
Carter, L.R., Prskawetz, A.: Examining structural shifts in mortality using the Lee-Carter method. Methoden und Ziele 39 (2001)
Berndt, D.J., Clifford, J.: Using dynamic time warping to find patterns in time series. In: AAAI 1994 Workshop on Knowledge Discovery in Databases, pp. 359–370 (1994)
Booth, H., Hyndman, R., Tickle, L., De Jong, P.: Lee-Carter mortality forecasting: a multi-country comparison of variants and extensions. Demogr. Res. 15, 289–310 (2006). https://doi.org/10.4054/DemRes.2006.15.9
Box, G.E., Tiao, G.C.: Intervention analysis with applications to economic and environmental problems. J. Am. Stat. Assoc. 70(349), 70–79 (1975). https://doi.org/10.2307/2285379
Brouhns, N., Denuit, M., Vermunt, J.K.: A Poisson log-bilinear regression approach to the construction of projected lifetables. Insur. Math. Econ. 3(31), 373–393 (2002). https://doi.org/10.1016/S0167-6687(02)00185-3
Diebold, F.X., Mariano, R.S.: Comparing predictive accuracy. J. Bus. Econ. stat. 20(1), 134–144 (2002). https://doi.org/10.2307/1392185
Geweke, J.: Contemporary Bayesian Econometrics and Statistics. Wiley, Hoboken (2005)
Harvey, D., Leybourne, S., Newbold, P.: Testing the equality of prediction mean squared errors. Int. J. Forecast. 13(2), 281–291 (1997). https://doi.org/10.1016/S0169-2070(96)00719-4
Hryniewicz, O., Kaczmarek, K.: Bayesian analysis of time series using granular computing approach. Appl. Soft Comput. J. 47, 644–652 (2016). https://doi.org/10.1016/j.asoc.2014.11.024
Hryniewicz, O., Kaczmarek, K.: Monitoring of short series of dependent observations using a control chart approach and data mining techniques. In: Proceedings of the International Workshop ISQC 2016, Helmut Schmidt Universität, Hamburg, pp. 143–161 (2016)
Hryniewicz, O., Kaczmarek-Majer, K.: Monitoring of short series of dependent observations using a XWAM control chart. In: Knoth, S., Schmid, W. (eds.) Frontiers in Statistical Quality Control 12 (2018)
Hyndman, R.J., Khandakar, Y.: Automatic time series forecasting: the forecast package for R. J. Stat. Softw. 26(3) (2008)
Kaczmarek-Majer, K., Hryniewicz, O.: Data-mining approach to finding weights in the model averaging for forecasting of short time series. In: Kacprzyk, J., Szmidt, E., Zadrożny, S., Atanassov, K.T., Krawczak, M. (eds.) IWIFSGN/EUSFLAT -2017. AISC, vol. 642, pp. 314–327. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-66824-6_28
Kaczmarek, K., Hryniewicz, O., Kruse, R.: Human input about linguistic summaries in time series forecasting. In: Proceedings of The Eighth International Conference on Advances in Computer-Human Interactions ACHI (2015)
Koissi, M.-C., Shapiro, A.F., Hgns, G.: Evaluating and extending the Lee-Carter model for mortality forecasting: bootstrap confidence interval. Insur. Math. Econ. 38(1), 1–20 (2006)
Kruse, R., Borgelt, C., Braune, C., Mostaghim, S., Steinbrecher, M.: Computational Intelligence: A Methodological Introduction. TCS. Springer, London (2016). https://doi.org/10.1007/978-1-4471-7296-3
Lee, R.D., Carter, L.R.: Modeling and forecasting US mortality. J. Am. Stat. Assoc. 87(419), 659–671 (1992). https://doi.org/10.2307/2290201
Lee, R.: The Lee-Carter method for forecasting mortality, with various extensions and applications. North Am. Actuar. J. 4(1), 80–91 (2000). https://doi.org/10.1080/10920277.2000.10595882
Makridakis, S., Hibon, M.: The M3-competition: results, conclusions and implications. Int. J. Forecast. 16, 451–476 (2000). https://doi.org/10.1016/S0169-070(00)00057-1
McKee, M., Zatoski, W.: How the cardiovascular burden of illness is changing in eastern Europe. Evid.-Based Cardiovasc. Med. 2(2), 39–41 (1998)
Watson, P.: Explaining rising mortality among men in Eastern Europe. Soc. Sci. Med. 41(7), 923–934 (1995). https://doi.org/10.1016/0277-9536(94)00405-I
Fund Pension Protection: The Pensions Regulator (2006), The Purple Book: DB Pensions Universe Risk Profile (2008)
Lundström, H., Qvist, J.: Mortality forecasting and trend shifts: an application of the Lee-Carter model to Swedish mortality data. Int. Statist. Rev. 72, 37–50 (2004). https://doi.org/10.1111/j.1751-5823.2004.tb00222.x
Tuljapurkar, S., Li, N., Boe, C.: A universal pattern of mortality decline in the G7 countries. Nature 405(6788), 789–792 (2000). https://doi.org/10.1038/35015561
Wang, D., Lu, P.: Modelling and forecasting mortality distributions in England and Wales using the Lee-Carter Model. J. Appl. Statist. 32, 873–885 (2005). https://doi.org/10.1080/02664760500163441
Felipe, A., Guillén, M., Perez-Marin, A.M.: Recent mortality trends in the Spanish population. Br. Actuar. J. 4(8), 757–786 (2002). https://doi.org/10.1017/S1357321700003901
Lovász, E.: Analysis of Finnish and Swedish mortality data with stochastic mortality models. Eur. Actuar. J. 2(1), 259–289 (2011). https://doi.org/10.1007/s13385-011-0039-8
Cairns, A.J.G., Blake, D., Dowd, K., Coughlan, G.D., Epstein, D., Khalaf-Allah, M.: Mortality density forecasts: an analysis of six stochastic mortality models. Insur.: Math. Econ. 3(48), 355–367 (2011). https://doi.org/10.1016/j.insmatheco.2010.12.005
Cairns, A.J.G., Blake, D., Dowd, K.: A two-factor model for stochastic mortality with parameter uncertainty: theory and calibration. J. Risk Insur. 73(4), 687–718 (2006). https://doi.org/10.1111/j.1539-6975.2006.00195.x
Macdonald, A., Gallop, A., Miller, K., Richards, S., Shah, R., Willets, R.: Stochastic projection methodologies: Lee-Carter model features, example results and implications. Continuous Mortality Investigation Bureau, Working Paper No. 25 (2007)
Renshaw, A.E., Haberman, S.: A cohort-based extension to the Lee-Carter model for mortality reduction factors. Insur.: Math. Econ. 38(3), 556–570 (2006). https://doi.org/10.1016/j.insmatheco.2005.12.001
Wang, X., Mueen, A., Ding, H., Trajcevski, G., Scheuermann, P., Keogh, E.: Experimental comparison of representation methods and distance measures for time series data. Data Min. Knowl. Disc. 26, 275–309 (2013). https://doi.org/10.1007/s10618-012-0250-5
Wilmoth, J.R., Andreev, K., Jdanov, D., Glei, D.A., Boe, C., Bubenheim, M., Philipov, D., Shkolnikov, V., Vachon, P.: Methods protocol for the human mortality database. University of California, Berkeley, and Max Planck Institute for Demographic Research, Rostock (2017). http://www.mortality.org/Public/Docs/MethodsProtocol.pdf. Version 6: Accessed 27 Nov 2017
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG, part of Springer Nature
About this paper
Cite this paper
Bartkowiak, M., Kaczmarek-Majer, K., Rutkowska, A., Hryniewicz, O. (2018). Model Averaging Approach to Forecasting the General Level of Mortality. In: Medina, J., et al. Information Processing and Management of Uncertainty in Knowledge-Based Systems. Theory and Foundations. IPMU 2018. Communications in Computer and Information Science, vol 853. Springer, Cham. https://doi.org/10.1007/978-3-319-91473-2_39
Download citation
DOI: https://doi.org/10.1007/978-3-319-91473-2_39
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-91472-5
Online ISBN: 978-3-319-91473-2
eBook Packages: Computer ScienceComputer Science (R0)