## Abstract

Epidemiologic cohort studies typically involve the follow-up of large population groups over many years to ascertain the effects of environmental exposures on the outbreak of illness and the age and cause of death. An efficient method of analysis is to fit Poisson regression models to grouped data consisting of a multidimensional classification of disease cases and person-years of observation by discrete categories of age, calendar period, and various aspects of exposure. Extension of these models for use with disease rates and exposure variables that vary continuously with age or time leads to the well-known proportional hazards model. Incorporation of external standard rates is more likely to improve the estimates of exposure effects in additive or excess risk models than in multiplicative or relative risk situations. Examples are provided of the maximum likelihood fitting of such models to data from cohort studies of British doctors and Montana smelter workers. The discussion considers the choice between models and certain problems that may arise when attempting to fit nonmultiplicative relationships.

## Key words and phrases

efficiency excess risk healthy worker effect Poisson regression proportional hazards relative risk standardized mortality ratio## Preview

Unable to display preview. Download preview PDF.

## Bibliography

- Aalen, O. (1978). “Nonparametric inference for a family of counting processes.”
*Ann. Statist*.,**6**, 701–726.MathSciNetzbMATHCrossRefGoogle Scholar - Andersen, P. K. and Gill, R. D. (1982). “Cox’s regression model for counting processes: A large sample study.”
*Ann. Statist*.,**10**, 1100–1120.MathSciNetzbMATHCrossRefGoogle Scholar - Aranda-Ordaz, F. J. (1983). “An extension of the proportional hazards model for grouped data.”
*Biometrics*,**39**, 109–117.MathSciNetzbMATHCrossRefGoogle Scholar - Armitage, P. (1955). “Tests for linear trend in proportions and frequencies.”
*Biometrics*,**11**, 375–386.CrossRefGoogle Scholar - Armitage, P. (1971).
*Statistical Methods in Medical Research*. Oxford: Blackwell.Google Scholar - Armitage, P. and Doll, R. (1961). “Stochastic models for carcinogenesis.” In
*Proceedings of the Fourth Berkeley Symposium on Mathematical Statistics and Probability*,**4**, 19–38.Google Scholar - Baker, R. J. and Nelder, J. A. (1978).
*The GLIM System: Release 3*. Oxford: Numerical Algorithms Group.Google Scholar - Beaumont, J. J. and Breslow, N. E. (1981). “Power considerations in epidemiologic studies of vinyl chloride workers.”
*Amer. J. Epidemiology*,**114**, 725–734.Google Scholar - Beebe, G. W. (1981). “The atomic bomb survivors and the problem of low dose radiation effects.”
*Amer. J. Epidemiology*,**114**, 761–783.Google Scholar - Berry, G. (1980). “Dose-response in case-control studies.”
*Epidemiology and Community Health*, 34, 217–222.CrossRefGoogle Scholar - Berry, G. (1983). “The analysis of mortality by the subject-years method.”
*Biometrics*,**39**, 173–184.CrossRefGoogle Scholar - Berry, G., Gilson, J. C., Holmes, S., Lewinsohn, H. C., and Roach, S. A. (1979). “Asbestosis: A study of dose-response relationship in an asbestos textile factory.”
*British J. Industrial Medicine*,**36**, 98–112.Google Scholar - Breslow, N. E. (1972). “Contribution to discussion of paper by D. R. Cox.”
*J. Roy. Statist. Soc. Ser. B*,**34**, 216–217.MathSciNetGoogle Scholar - Breslow, N. (1981). “Odds ratio estimators when the data are sparse.”
*Biometrika*,**68**, 73–84.MathSciNetzbMATHCrossRefGoogle Scholar - Breslow, N. (1982). “Design and analysis of case-control studies.”
*Annual Rev. Public Health*,**3**, 29–54.CrossRefGoogle Scholar - Breslow, N. (1984). “Elementary methods of cohort analysis.”
*Internat. J. Epidemiology*,**13**, 112–115.CrossRefGoogle Scholar - Breslow, N. E. and Day, N. E. (1980).
*Statistical Methods in Cancer Research I: The Analysis of Case-Control Studies*. Lyon: International Agency for Research on Cancer.Google Scholar - Breslow, N. E., Lubin, J. H., Marek, P., and Langholz, B. (1983). “Multiplicative models and cohort analysis.”
*J. Amer. Statist. Assoc*.,**78**, 1–12.zbMATHCrossRefGoogle Scholar - Brown, C. C. and Chu, K. C. (1983). “Implications of the multistage theory of carcinogenesis applied to occupational arsenic exposure.”
*J. Natl. Cancer Inst*.,**70**, 455–463.Google Scholar - Clayton, D. G. (1982). “The analysis of prospective studies of disease aetiology.”
*Comm. Statist. A—Theory Methods*,**11**, No. 19, 2129–2155.MathSciNetCrossRefGoogle Scholar - Cochran, W. G. (1954). “Some methods for strengthening the common χ
^{2}tests.”*Biometrics*,**10**, 417–451.MathSciNetzbMATHCrossRefGoogle Scholar - Cox, D. R. (1972). “Regression models and life tables (with discussion).”
*J. Roy. Statist. Soc. Ser. B*,**34**, 187–220.MathSciNetzbMATHGoogle Scholar - Cox, D. R. (1975). “Partial likelihood.”
*Biometrika*,**62**, 269–276.MathSciNetzbMATHCrossRefGoogle Scholar - Cox, D. R. and Hinkley, D. V. (1974).
*Theoretical Statistics*. London: Chapman and Hall.zbMATHGoogle Scholar - Doll, R. and Hill, A. B. (1964). “Mortality in relation to smoking: Ten years’ observations on British doctors.”
*British Medical J*.,**1**, 1399–1410, 1460–1467.CrossRefGoogle Scholar - Doll, R. and Hill, A. B. (1966). “Mortality of British doctors in relation to smoking: Observations on coronary thrombosis.”
*Natl. Cancer Inst. Monogr*.,**19**, 205–268.Google Scholar - Doll, R. and Peto, R. (1976). “Mortality in relation to smoking: 20 years’ observations on male British doctors.”
*British Medical J*.,**2**, 1525–1536.CrossRefGoogle Scholar - Doll, R. and Peto, R. (1978). “Cigarette smoking and bronchial carcinoma: Dose and time relationships among regular smokers and lifelong non-smokers.”
*J. Epidemiology and Community Health*,**32**, 303–313.CrossRefGoogle Scholar - Fienberg, S. E. (1980).
*The Analysis of Cross-Classified Data*, 2nd edn. Cambridge, MA: MIT Press.zbMATHGoogle Scholar - Fienberg, S. E. and Mason, W. M. (1985). “Specification and implementation of age, period and cohort models.” In W. M. Mason and S. E. Fienberg (eds.),
*Cohort Analysis in Social Research: Beyond the Identification Problem*. New York: Springer-Verlag, 45–88.Google Scholar - Fox, A. J. and Collier, P. F. (1976). “Low mortality rates in industrial cohort studies due to selection for work and survival in the industry.”
*British. J. Preventive and Social Medicine*,**30**, 225–230.Google Scholar - Frome, E. L. (1983). “The analysis of rates using Poisson regression models.”
*Biometrics*,**39**, 665–674.zbMATHCrossRefGoogle Scholar - Frost, W. H. (1939). “The age selection of mortality from tuberculosis in successive decades.”
*Amer. J. Hygiene A*,**30**, 91–96.Google Scholar - Gilbert, E. S. (1983). “An evaluation of several methods for assessing the effects of occupational exposure to radiation.”
*Biometrics*,**39**, 161–171.CrossRefGoogle Scholar - Gill, R. (1980).
*Censoring and Stochastic Integrals*. Amsterdam: Mathematical Centre Tracts.zbMATHGoogle Scholar - Hammond, E. C. (1966). “Smoking in relation to the death rates of one million men and women.”
*Natl. Cancer Inst. Monogr*.,**19**, 127–204.Google Scholar - Hauck, W. W. (1979). “The large sample variance of the Mantel-Haenszel estimator of a common odds ratio.”
*Biometrics*,**35**, 817–820.MathSciNetzbMATHCrossRefGoogle Scholar - Holford, T. R. (1980). “The analysis of rates and of survivorship using log-linear models.”
*Biometrics*,**36**, 299–306.zbMATHCrossRefGoogle Scholar - Johansen, S. (1981). “Discussion of paper by D. Oakes.”
*Internat. Statist. Rev*.,**49**, 258–262.Google Scholar - Kalbfleisch, J. D. and Prentice, R. L. (1980).
*The Statistical Analysis of Failure Time Data*. New York: Wiley.zbMATHGoogle Scholar - Kleinbaum, D. G., Kupper, L. L., and Morgenstern, H. (1982).
*Epidemiologic Research*. Belmont: Wadsworth.Google Scholar - Knox, E. G. (1973). “Computer simulation of industrial hazards.”
*British J. Industrial Medicine*,**30**, 54–63.Google Scholar - Laird, N. and Olivier, D. (1981). “Covariance analysis of censored survival data using log-linear analysis techniques.”
*J. Amer. Statist. Assoc*.,**76**, 231–240.MathSciNetzbMATHCrossRefGoogle Scholar - Lee, A. M. and Fraumeni, J. F. (1969). “Arsenic and respiratory cancer in man: An occupational study.”
*J. Natl. Cancer Inst*.,**42**, 1045–1052.Google Scholar - Lee-Feldstein, A. (1983). “Arsenic and respiratory cancer in humans: Follow-up of copper smelter employees in Montana.”
*J. Natl. Cancer Inst*.,**70**, 601–610.Google Scholar - Lehman, E. L. (1959).
*Testing Statistical Hypotheses*. New York: Wiley.Google Scholar - Lundin, F. E., Archer, V. E., and Wagoner, J. K. (1979). “An exposure-time-response model for lung cancer mortality in uranium miners: Effects of radiation exposure, age, and cigarette smoking.” In N. E. Breslow and A. Whittemore (eds.),
*Energy and Health*. Philadelphia: SIAM, 243–264.Google Scholar - Maahon, B. and Pugh, T. F. (1970).
*Epidemiology: Principles and Methods*. Boston: Little, Brown.Google Scholar - Mantel, N. and Haenszel, W. (1959). “Statistical aspects of the analysis of data from retrospective studies of disease.”
*J. Natl. Cancer Inst*.,**22**, 719–748.Google Scholar - Moolgavkar, S. H., Lustbader, E. D., and Venzon, D. J. (1984). “A geometric approach to nonlinear regression diagnostics with application to matched case-control studies.”
*Ann. Statist*.,**12**, 816–826.MathSciNetzbMATHCrossRefGoogle Scholar - Nelder, J. A. and Wedderburn, R. W. M. (1972). “Generalized linear models.”
*J. Roy. Statist. Soc. A*,**135**, 370–384.CrossRefGoogle Scholar - Oakes, D. (1977). “The asymptotic information in censored survival data.”
*Biometrika*,**64**, 441–448.MathSciNetzbMATHCrossRefGoogle Scholar - Oakes, D. (1981). “Survival times: Aspects of partial likelihood.”
*Internat. Statist. Rev*.,**49**, 235–264.MathSciNetzbMATHCrossRefGoogle Scholar - Pregibon, D. (1981). “Logistic regression diagnostics.”
*Ann. Statist*.,**9**, 705–724.MathSciNetzbMATHCrossRefGoogle Scholar - Prentice, R. L. and Self, S. (1983). “Asymptotic distribution theory for Cox-type regression models with general relative risk form.”
*Ann. Statist*.,**11**, 804–813.MathSciNetzbMATHCrossRefGoogle Scholar - Rao, C. R. (1965).
*Linear Statistical Inference and its Applications*. New York: Wiley.zbMATHGoogle Scholar - Richards, F. S. G. (1961). “A method of maximum likelihood estimation.”
*Roy. Statist. Soc. Ser. B*,**23**, 469–473.MathSciNetzbMATHGoogle Scholar - Rothman, K. J. (1974). “Synergy and antagonism in cause-effect relationships.”
*Amer. J. Epidemiology*,**99**, 385–388.Google Scholar - Rothman, K. J. and Boice, J. D. (1979).
*Epidemiologic Analysis with a Programmable Calculator*. NIH Publication 79–1649. Washington: U.S. Government Printing Office.Google Scholar - Roueché, B. (1967).
*Annals of Epidemiology*. Boston: Little, Brown.Google Scholar - Schlesselman, J. J. (1982).
*Case-Control Studies: Design, Conduct and Analysis*. New York: Oxford U.P.Google Scholar - Selikoff, I. J., Hammond, E. C., and Seidman, H. (1980). “Latency of asbestos disease among insulation workers.”
*Cancer*,**46**, 2736–2740.CrossRefGoogle Scholar - Storer, B. E., Wacholder, S., and Breslow, N. E. (1983). “Maximum likelihood fitting of general risk models to stratified data.”
*Appl. Statist*.,**32**, 177–181.CrossRefGoogle Scholar - Tarone, R. E. (1982). “The use of historical control information in testing for a trend in Poisson means.” Biometrics,
**38**, 457–462.CrossRefGoogle Scholar - Thomas, D. C. (1977). “Addendum to a paper by Liddel, F. D. K., McDonald, J. C. and Thomas, D. C.”
*J. Roy. Statist. Soc. Ser. A*, 483–485.Google Scholar - Thomas, D. C. (1981). “General relative risk models for survival time and matched case-control analysis.”
*Biometrics*,**37**, 673–686.CrossRefGoogle Scholar - Thomas, D. C. (1982). “Temporal effects and interactions in cancer: Implications of carcinogenic models.” In R. L. Prentice and A. S. Whittemore (eds.),
*Environmental Health: Risk Assessment*, Philadelphia: SIAM, 107–121.Google Scholar - Thompson, R. and Baker, R. (1981). “Composite link functions in generalized linear models.”
*Appl. Statist*.,**30**, 125–131.MathSciNetzbMATHCrossRefGoogle Scholar - Wall, W. D. and Williams, H. L. (1970).
*Longitudinal Studies and the Social Sciences*. London: Heinemann.Google Scholar - White, E. (1982). “A two stage design for the study of the relationship between a rare exposure and a rare disease.”
*Amer. J. Epidemiology*,**115**, 119–128.Google Scholar - Whitehead, J. (1980). “Fitting Cox’s regression model to survival data using GLIM.”
*Appl. Statist*.,**29**, 268–275.MathSciNetzbMATHCrossRefGoogle Scholar - Whittemore, A. and Altshuler, B. (1976). “Lung cancer incidence in cigarette smokers: Further analysis of Doll and Hill’s data on British physicians.”
*Biometrics*,**32**, 805–816.CrossRefGoogle Scholar - Yule, G. U. (1934). “On some points relating to vital statistics, more especially statistics of occupational mortality.”
*J. Roy. Statist. Soc*.,**94**, 1–84CrossRefGoogle Scholar