Human Mortality Modeling with a Fuzzy Approach Based on Singular Value Decomposition Technique
Modeling and forecasting human mortality are significant research topics in several disciplines because mortality rates are fundamental in planning and policy decisions. Among various techniques, Lee Carter (LC) model is one of the most popular stochastic
- PDF / 1,890,896 Bytes
- 19 Pages / 439.37 x 666.142 pts Page_size
- 55 Downloads / 244 Views
Abstract. Modeling and forecasting human mortality are significant research topics in several disciplines because mortality rates are fundamental in planning and policy decisions. Among various techniques, Lee Carter (LC) model is one of the most popular stochastic method in human mortality modeling. The original LC model was fuzzified to eliminate the assumptions related with homoscedasticity. The existing fuzzy model makes use of ordinary least squares (OLS) technique, which prevents the model to capture the existing fluctuations in data. In this study, a revised version of fuzzy LC model utilizing singular value decomposition (SVD) technique is proposed to overcome this issue. After modeling the mortality rates, their future values are forecasted by a modified first order fuzzy time series technique. For illustration purposes, proposed method is applied to mortality data of Finland. Numerical outputs show that proposed method is statistically better in modeling mortality compared to the existing fuzzy method. In addition, the modified fuzzy time series technique generates better forecasts than the original version. Keywords: Fuzzy modeling Lee Carter method decomposition Fuzzy regression Fuzzy time series modeling
Singular value Human mortality
1 Introduction It is known that human mortality modeling and forecasting play significant roles in strategy development and decision making in diverse sectors. Mortality modeling finds application areas in projecting and forecasting life expectancies, age distributions, unemployment rates, labor force compositions, household consumptions and etc. Together with fertility and migration rates, mortality rates constitute the vital demographic indicators of population dynamics [1]. Age-specific population estimates of immediate future or long-term forecasts based on these vital demographic indicators shape the policies in allocating the resources among public and private investments and the future population [2]. The outputs of the models obtained from fertility, mortality and migration elements form the basis for medium or long term planning in various areas such as labor market [3], public financing [4], insurance and pensions sector [5, 6], education system [2], healthcare services [7], and etc. © Springer International Publishing AG 2017 J.J. Merelo et al. (eds.), Computational Intelligence, Studies in Computational Intelligence 669, DOI 10.1007/978-3-319-48506-5_11
198
D.F. Demirel and M. Basak
Population modeling and estimations are performed via diverse methodologies which can basically be grouped as population projection methods and population forecasting methods. The projection methods simply rely on deterministic scenarios for different components of mortality, fertility and migration value combinations [8]. Setting the values of these components generally requires formation of a group of experts. In contrast, population forecasting makes use of historical data to obtain a future population estimate using a stochastic approach which takes component uncertainti
Data Loading...
