Abstract
The test for the hypothesis that the mortality in the observed group is the same as that of a reference group by subject-years method is considered in this paper. We prove a Berry-Esséen type theorem for the test statistics studied in Berry (1983), which gives an upper bound for the convergence rates of test statistics to their limiting distributions.
Similar content being viewed by others
References
Barndorff-Nielsen OE, Hall P (1988) On the level-error after Bartlett adjustment of the likelihood ratio statistic. Biometrika 75:374–378
Berry G (1983) The analysis of mortality by the subject-years method. Biometrics 39:173–184
Case RAM, Lea AJ (1955) Mustared gas poisoning, choronic bronchities and lung cancer. British J of Preventive and Social Med 9:62–72
Kalbfleisch JD, Prentice RL (1982) The Statistical Analysis of Failure Time Data. Wiley, New York
Keiding N (1987) The method of expected number of deaths, 1786–1886–1986. Intern Statist Rev 55:1–20
Petrov VV (1975) Sums of Independent Random Variables. Springer, Berlin
Rao C, Radhakrishna (1947) Large sample tests of statistical hypotheses concerning several parameters with applications to problems of estimation. Proc Comb Phil Soc 44:50–57
Serfling RJ (1980) Approximation Theorems of Mathematical Statistics. Wiley, New York
Tu DS (1989) Mortality analysis by subject-years method in the presence of mixed censoring. Technical Report 89-12. Center for Multivariate Analysis, The Penn State University
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Tu, D.S. The Berry-esséen theorem for the subject-years method in mortality analysis with censored data. Metrika 38, 269–283 (1991). https://doi.org/10.1007/BF02613621
Received:
Revised:
Issue Date:
DOI: https://doi.org/10.1007/BF02613621