Stochastic population forecasts using functional data models for mortality, fertility and migration

Abstract

Age-sex-specific population forecasts are derived through stochastic population renewal using forecasts of mortality, fertility and net migration. Functional data models with time series coefficients are used to model age-specific mortality and fertility rates. As detailed migration data are lacking, net migration by age and sex is estimated as the difference between historic annual population data and successive populations one year ahead derived from a projection using fertility and mortality data. This estimate, which includes error, is also modeled using a functional data model. The three models involve different strengths of the general BoxCox transformation chosen to minimise out-of-sample forecast error. Uncertainty is estimated from the model, with an adjustment to ensure the one-step-forecast variances are equal to those obtained with historical data. The three models are then used in the Monte Carlo simulation of future fertility, mortality and net migration, which are combined using the cohort-component method to obtain age-specific forecasts of the population by sex. The distribution of forecasts provides probabilistic prediction intervals. The method is demonstrated by making 20-year forecasts using Australian data for the period 1921-2003.

Problems of Social-Economic and Demographic Development of Agricultural Population (Based on the Data of the Republic of Tatarstan)

“…The corresponding uncertainty is created mainly due to the complexity of understanding demographic processes, imperfect demographic data, unpredictability of migration policy, and a number of other phenomena [11,12,13].…”

Point and interval forecasts of age-specific life expectancies

“…, e 2 n (x)}; (5) J < n is the optimal number of functional principal components used. Following Hyndman and Booth (2008) and Shang, Booth, and Hyndman (2011), we chose J = 6 which should be larger than any of the components required. 3.…”

Proyección estocástica de la mortalidad mexicana por medio del método de Lee-Carter / Stochastic Projection of Mexican Mortality through the Lee-Carter Method

“…En el aspecto metodológico ha habido algunos intentos por tomar en cuenta la incertidumbre inherente a toda prefiguración del futuro. Entre los principales trabajos sobre proyecciones estocásticas se encuentran los de Sykes (1969), Le Bras (1971), Saboia (1974Saboia ( y 1977, Heyde y Cohen (1985), Cohen (1986), Alho y Spencer (2005), Alho (1985Alho ( y 1990, Lee (1993Lee ( y 1974, Lee y Carter (1992), Lee y Tuljapurkar (1994) y, recientemente, Hyndman y Booth (2008).…”