Why fitting a parametrized survival function does not give a reliable life table

• Autorzy: Euert van Imhoff , Ewa Tabeau
• Języki publikacji: EN

Abstrakty

EN

Age-specific mortality could be represented by at least four variables: the survival function, the probability of dying, the probability of surviving and the hazard ratę, strictly related to each other. Assuming that one of these variables can be described by a continous function of age, it has been shown that the survival function cannot be taken as a point of departure for fitting the parametrized functions. Starting from the survival function i.e. having its well fitted curve does not ąuarantee well- fitting for other variables(original abstract)

Słowa kluczowe

EN

Mortality; Mortality statistics; Life table

PL

Umieralność; Statystyka umieralności; Tablice trwania życia

• Czasopismo: Studia Demograficzne
• Rocznik: 1998
• Numer: nr 1(131)
• Strony: 15--26

Twórcy

autor

Euert van Imhoff

autor

Ewa Tabeau

Bibliografia

• Anson J., 1988, The Parameters of Death: A Consideration of the Quantity of Information in a Life Table Using a Polynomial Representation of the Survival Curve, "Statistics in Medicine", 7, 895-912.
• Cramer J.S., 1986, Econometric Applications of Maximum Likelihood Methods, Cambridge: Cambridge University Press.
• Hall R.E., Johnston J., Lilien D.M., 1990, Micro TSP: Users Manuał, Irvine, California: Quantitative Micro Software.
• Hartman M., 1989, Modelling Childhood Mortality, "Journal of Official Statistics", 5(3), 241-251.
• Hartman M., 1980, Infant and Childhood Mortality, Working Paper, University of Lund.
• Horiuchi S., Coale A.J, 1990, Age Patterns of Mortality for Older Women: An Analysis Using the Age-Specific Ratę of Mortality Change With Age, "Mathematical Population Studies", 2(4), -245-267.
• Hoem J.M., 1972, On^the Theory of Analytic Graduation, in: Proceedings of the Sixth Berkeley Syinposium on Mathematical Statistics and Probability, Berkeley, University of*California Press.
• Keyfitz N., 1982, Choice of Function for Mortality Analysis: Effectwe Forecasting Depends on a Minimum Parameter Representation, "Theoretical Population Biology", 21, 329-352.
• Modę C.J., Busby R.C, 1982, An Eight-Parameter Model of Human Mortality. The Single Decrement Case, "Bulletin of Mathematical Biology", 44(5), 647-659.
• Petrioli L., 1981, A New Set of Models of Mortality, Conference Paper, IUSSP Seminar on Methodology and Data Collection in Mortality Studies, Dakar, Senegal, 7-10 July, 1981.
• Rogers A., Little J.S., 1994, Parametrizing Age Patterns of Demographic Rates with the Multiexponential Model Schedule, "Mathematical Population Studies", 4(3), 175-195.
• Tabeau E., van Poppel F., Willekens F., 1994, Parametrization Functions in Mortality Analyses: Selecting the Dependent Variable and Measuring the Goodness ofFit, Submitted.
• Van Imhoff E., 1991, Profile: a Program for Estimating the Coefficients of Demographic Age-Intensity Profiles, NIDI Report The Hague: NIDI.