A general outline of the statistical issues in the design and analysis of carcinogenicity bioassays is given in this paper. Design issues, such as assignment of animals to treatment groups, dual control groups, duration of study, and the number of animals per group are discussed. Information needed by the biostatistician are listed to facilitate the recording of data by the pathologist. Issues in the analysis of tumor incidence data are given. Use of historical control data is encouraged and discussed.
References
1.
1. Gart, JJ, Chu, KC, and Tarone, RE: Statistical issues in interpretation of chronic bioassay tests for carcinogenicity. J. Natl. Cancer Inst.62: 957–974, 1979.
2.
2. Siegel, S: Non-parametric Statistics for the Behavioral Sciences.McGraw-Hill, New York, 1956, pp. 96–104.
3.
3. Fieiss, JL: Statistical Methods for Rates and Proportions.John Wiley & Sons, New York, 1973, pp. 14–22.
4.
4. Armitage, P: Statistical Methods in Medical Research.Blackwell Scientific Publications, Oxford, 1971, pp. 362–365.
5.
5. Thomas. DG, Breslow, N and Gart, JJ: Trend and homogeneity analyses of proportions and life table data. Computers and Biomedical Research10: 373–381, 1977.
6.
6. Peto, R, Pike, MC, Day, NE, et al: Guidelines for simple, sensitive significance tests for carcinogenic effects in long-term animal experiments in IARC Monographs on the Evaluation of the Carcinogenic Risk of Chemicals to Humans, Supplement 2.IARC, Lyon1980, pp. 311–426.
7.
7. Haseman, JK: Patterns of tumor incidence in two-year cancer bioassay feeding studies in Fischer 344 rats. Fundamental and Applied Toxicology3: 1–9, 1983.
8.
8. Tarone, RE: The use of historical control information in testing for a trend in proportions. Biometrics38: 215–220, 1982.
