ON RELIABILITY APPROACH AND STATISTICAL INFERENCE IN DEMOGRAPHY
Keywords:
Demography, Chi-square test, Mortality table, Composite hypothesis, Censoring, Gompertz model, Makeham model, Weibull model, ML estimators, NRR statistic.Abstract
In demography, Gompertz and Makeham models have significant role in modeling and in analysis of mortality and ageing. Till the end of the 20th century, researchers have used the tables of mortalities (also called life tables) for demographic analysis but in the end of the 20th century due to the development in statistical methods of survival analysis and reliability one can treat the individuals data even with the information of censoring. The Gompertz, Makeham, and Weibull models are compared with respect to the goodness-of-fit to the table of mortality and to the individuals data in the presence of censoring. For data from the table of mortality, the test statistic considered by Gerville-Reache and Nikulin (2000) is used. For censored individual data the chi-squared type test proposed by Bagdonavicius et al. (2010) is used.
Downloads
References
Akritas, M.G. (1988). Pearson-type goodness of fit tests: the univariate case. J.
Amer. Statist. Assoc., 83, p. 222-230.
Bagdonavicius, V. and Nikulin, M. (2002). Accelerated Life Models.
Chapman and Hall/CRC, Boca Raton.
Bagdonavicius, V., Kruopis, J. and Nikulin M. (2010). Nonparametric tests
for Censored Data. ISTE and J.Wiley.
Bagdonavicius, V. and Nikulin, M. (2011). Chi-square goodness-of-fit test for
right censored data. Int. J. Appl. Math. Stat. Vol.24, Issue No.SI-11A, p. 30-
Drost, F. (1988). Asymptotics for generalized chi-squared goodness-of-fit
tests. CWI Tracs, Amsterdam: Centre for Mathematics and Computer
Sciences, V.48.
Gavrilov, L.A. and Gavrilova, N. S. (1991). The Biology of Life Span: A
Quantitative Approach. New York: Harwood Academic Publisher.