The Cochran-Armitage Test for Trends or Thresholds in Proportions

  • S. Stanley Young
Chapter
Part of the Advances in Risk Analysis book series (AIRA, volume 5)

Abstract

The Cochran-Armitage test for trends or thresholds in proportions. Young, S. S. (1985) Society for Risk Analysis, 1985 Annual Meeting. the Cochran-Armitage (C-A) test (1954, 1955) is widely used as a test for linear trends in proportions in the analysis of long term rodent studies. Implicit in the use of this test is the assumption that the dose response pattern is known. Although in practice the dose response pattern is often assumed linear on a log dose scale, this test can be used to test for nonlinear dose response patterns. The effect of the choice of different dose response patterns is examined using hypothetical and actual examples of tumor data in rodents. The choice of a particular dose response pattern can greatly influence the p-value from the C-A test. As an alternative to the usual C-A test, a sequential testing procedure, similar to the Williams-t (Williams, 1971, 1972), is suggested. Under the assumption of a threshold model, this procedure gives improved testing and estimation and leads to better inferences.

Key Words

Cochran-Armitage test Bioassay Thresholds Trends DDT TDE DDE 
This is a preview of subscription content, log in to check access.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Anderson, R. L. and L. A. Nelson. “A family of models involving intersecting straight lines and concomitant experimental designs useful in evaluating response to fertilizer nutrients” Biometrics 31: 303–318 (1975).CrossRefGoogle Scholar
  2. Anolymous. “Bioassay of DDT, TDE, and p,p’-DDE for possibleGoogle Scholar
  3. carcinogenicity“ NCI Technical Report, No. 131. (1978).Google Scholar
  4. Armitage, P. “Tests for linear trends in proportions and frequencies Biometrics 11:375–386 (1955).CrossRefGoogle Scholar
  5. Board of Scientific Counselors, NTP. Report of the ad hoc panel on chemical carcinogenesis testing and evaluation. U.S. Dept. of Health and Human Services. (1984).Google Scholar
  6. Cimino, J.A. Cancer and the Environment, Possible Mechanisms of Thresholds for Carcinogens and other Toxic Substances. Mary Ann Liebert. New York. (1983).Google Scholar
  7. Cochran, W.G. “Some methods of strengthening the common Chi-Square test” Biometrics 10: 417–451 (1954).CrossRefGoogle Scholar
  8. Daly, C. “A simple test for trends in a contingency table” Biometrics 18: 114–119 (1962).CrossRefGoogle Scholar
  9. Hendricks, J.D., T.P. Putman, D.D. Bills and R.O. Sinnhuber. “Inhibitory effect of a polychlorinated biphenyl (Aroclor 1254) on aflatoxin B1 carcinogenesis in rainbow trout (Salmo gairdneri)” JNCI 59: 1545–1551 (1977).PubMedGoogle Scholar
  10. Krewski, D., J. Kovar, and M. Bickis. “Optimal experimental designs for low dose extrapolation” In Topics in Applies Statistics edited by T.W. Dwived: Marcell Dekker, New York (1983).Google Scholar
  11. Littlefield, N.A., J.H. Farmer, D.W. Gaylor and W.G. Sheldon. “Effects of dose and time in a long-term low-dose carcinogenic study” Journal of Environmental Pathology and Toxicology 3: 17–34 (1979).Google Scholar
  12. Muller, K.E., C.N. Barton, and V.A. Benignus. “Recommendations for appropriate statistical practice in toxicology experiments” Neuro. Toxicology 5:113–126 (1984).Google Scholar
  13. Poon, A.H. “A Monte Carlo study of the power of some k-sample tests for ordered binomial alternatives” J. Stat. Comp. and Sim. 11: 251–259 (1980).CrossRefGoogle Scholar
  14. Portier, C. and D. Hoel. “Low-dose-rate extrapolation using the multistage model” Biometrics 39: 897–906 (1983).PubMedCrossRefGoogle Scholar
  15. Portier, C. and D. Hoel. “Optimal design of the chronic animal bioassay” J. Tox. Env. Health 12: 1–12 (1983).CrossRefGoogle Scholar
  16. Portier, C. and D. Hoel. “Design of animal carcinogenicity studies for goodness-of-fit of multistage models” Fundam. Appl. Toxic 4: 949–959 (1984).CrossRefGoogle Scholar
  17. Sheldon D.W., J.D. Hendricks, R.A. Coulombe, and G.S. Bailey. “Effect of dose on the inhibition of carcinogenesis/mutagenesis by Aroclor 1254 in rainbow trout fed aflatoxin B1” J. Tox. and Envir. Health 13: 649–657 (1984).CrossRefGoogle Scholar
  18. Shirley, Eryl A. C. “The comparison of treatment with control group means in toxicology studies” Applied Statistics 28: 144–151 (1979).CrossRefGoogle Scholar
  19. Squire, R.A. and Cameron, L.L. “An analysis of potential carcinogenic risk from formaldehyde” Regulatory Toxicology and Pharmacology 4: 107–129 (1984).PubMedCrossRefGoogle Scholar
  20. Tukey, J.W., Ciminera, J.L. and Heyse, J.E. “Testing the statistical certainty of a response to increasing doses of a response to increasing doses of a drug” Biometrics 41: 295–301 (1985).PubMedCrossRefGoogle Scholar
  21. Wahrendorf, J. “Simulatneous analysis of different tumor types in a long term carcinogenicity study with scheduled sacrifices” JNCI 70: 915–921 (1983).PubMedGoogle Scholar
  22. Williams, D.A. “A test for differences between treatment means when several dose levels are compared with a zero dose control” Biometrics 27: 103–117 (1971).PubMedCrossRefGoogle Scholar
  23. Williams, D.A. “The comparison of several dose levels with a zero dose control” Biometrics 28: 519–531 (1972).PubMedCrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media New York 1987

Authors and Affiliations

  • S. Stanley Young
    • 1
  1. 1.Statistical and Mathematical ServicesLilly Research LaboratoriesUSA

Personalised recommendations