Modeling and forecasting U. S. mortality

Abstract Time series methods are used to make long-run forecasts, with confidence intervals, of age-specific mortality in the United States from 1990 to 2065. First, the logs of the age-specific death rates are modeled as a linear function of an unobserved period-specific intensity index, with parameters depending on age. This model is fit to the matrix of U.S. death rates, 1933 to 1987, using the singular value decomposition (SVD) method; it accounts for almost all the variance over time in age-specific death rates as a group. Whereas e 0 has risen at a decreasing rate over the century and has decreasing variability, k(t) declines at a roughly constant rate and has roughly constant variability, facilitating forecasting. k(t), which indexes the intensity of mortality, is next modeled as a time series (specifically, a random walk with drift) and forecast. The method performs very well on within-sample forecasts, and the forecasts are insensitive to reductions in the length of the base period from 90 to 30 ...

[1]  H. L. Dunn,et al.  Vital statistics rates in the United States 1900-1940 , 1944 .

[2]  W. R. Buckland,et al.  A dictionary of statistical terms , 1958 .

[3]  Edgar F. Borgatta,et al.  Sociological Methodology, 1969. , 1969 .

[4]  I. J. Good,et al.  Some Applications of the Singular Decomposition of a Matrix , 1969 .

[5]  R. Lee,et al.  Estimating series of vital rates and age structures from Baptisms and burials: a new technique, with applications to pre-industrial England. , 1974, Population studies.

[6]  Ronald Lee.  Methods and Models for Analyzing Historical Series of Births, Deaths, and Marriages* , 1977 .

[7]  Nathan Keyfitz,et al.  Applied Mathematical Demography , 1978 .

[8]  Nathan Keyfitz,et al.  Choice of function for mortality analysis: Effective forecasting depends on a minimum parameter representation , 1982 .

[9]  Construction of the new United Nations model life table system. , 1982, Population bulletin of the United Nations.

[10]  D. Freedman,et al.  Bootstrapping an Econometric Model: Some Empirical Results , 1984 .

[11]  A Rogers,et al.  Parameterized multistate population dynamics and projections. , 1986, Journal of the American Statistical Association.

[12]  K C Land,et al.  Methods for national population forecasts: a review. , 1986, Journal of the American Statistical Association.

[13]  Wade Ah,et al.  Social Security area population projections: 1987. , 1988 .

[14]  G. Noble,et al.  Epidemiology of AIDS and HIV infection in the United States. , 1988 .

[15]  H. Jaffe,et al.  Epidemiology of HIV infection and AIDS in the United States. , 1988, Science.

[16]  J. Guralnik,et al.  Projecting the older population of the United States: lessons from the past and prospects for the future. , 1988, The Milbank quarterly.

[17]  S. Olshansky,et al.  On forecasting mortality , 1988 .

[18]  R. Brookmeyer,et al.  Methods for projecting course of acquired immunodeficiency syndrome epidemic. , 1988, Journal of the National Cancer Institute.

[19]  A. Coale,et al.  Revised regional model life tables at very low levels of mortality. , 1989, Population index.

[20]  J. Vallin,et al.  Quand certaines générations ont une mortalité différente de celle que l'on pourrait attendre , 1989 .

[21]  Coale Aj,et al.  Defects in data on old-age mortality in the United States: new procedures for calculating mortality schedules and life tables at the highest ages. , 1990 .

[22]  J. Wilmoth,et al.  Variation in vital rates by age, period, and cohort. , 1990, Sociological methodology.

[23]  J M Alho,et al.  Stochastic methods in population forecasting. , 1990, International journal of forecasting.

[24]  B D Spencer,et al.  Error models for official mortality forecasts. , 1990, Journal of the American Statistical Association.

[25]  A R Moss,et al.  Projections of AIDS morbidity and mortality in San Francisco. , 1990, JAMA.

[26]  A. Rogers,et al.  Forecasting cause-specific mortality using time series methods , 1992 .