Statistical Problems (and Some Solutions) Associated with Testing for Effects in Developmental Toxicology

  • R. Woodrow Setzer


We have come a long way in testing for effects in developmental toxicology since the debates over the “unit of observation” in teratology (Weil 1970; Kalter 1974; Staples and Haseman 1974; Becker 1974; Haseman and Hogan 1975). Much of the recent biostatistical work on testing has been on devising powerful statistical tests that reflect the proper choice for the unit of observation. This paper will review some of the statistical problems posed by developmental toxicology data as well as principal solutions posed for some of those problems. Included in the review are several simple new methods that have yet to be applied in this field. The analysis of developmental toxicology data would be improved through increased utilization of biological content that these new approaches offer.


Litter Size Rank Score Latent Variable Model Litter Effect Hazard Identification 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Becker BA (1974) The statistics of teratology. Teratology 9: 261–262.PubMedCrossRefGoogle Scholar
  2. Brownie C, Boos DD, Hughes-Oliver J (1990) Modifying the t and ANOVA F test when treatment is expected to increase variability relative to controls. Biometrics 46: 259–266.CrossRefGoogle Scholar
  3. Catalano P, Ryan L (submitted) Bivariate latent variable models for clustered discrete and continuous outcomes. submitted to J Am Stat A.Google Scholar
  4. Cochran WG (1943) Analysis of variance for percentages based on unequal numbers. J Am Stat A 38: 287–301.CrossRefGoogle Scholar
  5. Conover WJ, Salsburg DS (1988) Locally most powerful tests for detecting treatment effects when only a subset of patients can be expected to “respond” to treatment. Biom 44: 189–196.Google Scholar
  6. Endo A, Watanabe T (1988) Interlitter variability in fetal body weight in mouse offspring from continuous, overnight, and short-period matings. Teratology 37: 63–67.PubMedCrossRefGoogle Scholar
  7. Fujinaga M, Jackson EC, Baden JM (1990) Interlitter variability and developmental stage of day 11 rat embryos produced by overnight and morning short-period breeding regimens. Teratology 42: 535–540.PubMedCrossRefGoogle Scholar
  8. Gladen B (1979) The use of the jackknife to estimate proportions from toxicological data in the presence of litter effects. J Am Stat A 74: 278–283.CrossRefGoogle Scholar
  9. Good PI (1979) Detection of a treatment effect when not all experimental subjects will respond to treatment. Biom 35: 483–489.Google Scholar
  10. Haseman JK, Hogan MD (1975) Selection of the experimental unit in teratology studies. Teratology 12: 165–172.PubMedCrossRefGoogle Scholar
  11. Haseman JK, Kupper LL (1979) Analysis of dichotomous response data from certain toxicological experiments. Biom 35: 281–293.Google Scholar
  12. Holson JF, Scott WJ, Gaylor DW, Wilson JG (1976) Reduced interlitter variability in rats resulting from a restricted mating period, and reassessment of the “litter effect”. Teratology 14: 135–142.PubMedCrossRefGoogle Scholar
  13. Johnson RA, Verrill S, Moore DH (1987) Two-sample rank tests for detecting changes that occur in a small proportion of the treated population. Biom 43: 641–655.Google Scholar
  14. Kalter H (1974) The choice of the number of sampling units in teratology. Teratology 9: 257–258.PubMedCrossRefGoogle Scholar
  15. Kimmel CA, Young JF (1983) Correlating pharmacokinetics and teratogenic endpoints. Fund Appl Toxicol 3: 250–255.CrossRefGoogle Scholar
  16. Kleinman JC (1973) Proportions with extraneous variance: single and independent samples. J Am Stat A 68: 46–54.CrossRefGoogle Scholar
  17. Lefkopoulou M, Moore D, Ryan L (1989) The analysis of multiple correlated binary outcomes: Application to rodent teratology experiments. J Am Stat A 84: 810–815.CrossRefGoogle Scholar
  18. McCullagh P, Neider JA (1989) Generalized Linear Models. Second Edition. Chapman and Hall. London.Google Scholar
  19. Makuch RW, Stephens MA Escobar M (1989) Generalised binomial models to examine the historical control assumption in active control equivalence studies. The Statistician 38: 61–70.CrossRefGoogle Scholar
  20. Mankes RF, Renak V, Fieseher J, LeFevre R (1986) Birthweight depression in male rats contiguous to male siblings in utero exposed to high doses of 1,3-butanediol during organogenesis. JACT 5: 189–196.Google Scholar
  21. Marubini E, Correa Leite ML, Milani S (1988) Analysis of dichotomous response variables in teratology. Biom J 30: 965–974.CrossRefGoogle Scholar
  22. Meister R, Chahoud I, Jurgens M, Iverson F, Bochert G (1991) Biometrical analysis of strain differences and litter effects. To be published in the Springer Series (seen in manuscript).Google Scholar
  23. Moore DF (1987) Modelling the extraneous variance in the presence of extra-binomial variation. Appl Statist 36: 8–14.CrossRefGoogle Scholar
  24. Pack SE (1986) Hypothesis testing for proportions with overdispersion. Biom 42: 967–972.Google Scholar
  25. Setzer RW and Rogers JM (1988) The similarity of toxic response of neighboring fetuses in the same uterine horn in mice. Teratology 37: 491.Google Scholar
  26. Setzer RW and Rogers JM (1989) The relative powers of statistical tests for developmental toxicology data: maximum likelihood beta-binomial, maximum quasi-likelihood, and ANOVA based on the Freeman-Tukey binomial transform. Teratology 39: 481.Google Scholar
  27. Setzer RW (in prep) The power of statistical tests for developmental toxicology data.Google Scholar
  28. Smythe RT, Krewski D, Murdoch D (1986) The use of historical control information in modelling dose-response relationships in carcinogenesis. Statist Probab Lett 4: 87–93.CrossRefGoogle Scholar
  29. Sokal RR, Rohlf FJ (1981) Biometry. Second Edition. W.H. Freeman. San Francisco.Google Scholar
  30. Staples RE, Haseman JK (1974) Selection of appropriate experimental units in teratology. Teratology 9: 259–260.PubMedCrossRefGoogle Scholar
  31. Weil CS (1970) Selection of the valid number of sampling units and a consideration of their combination in toxicological studies involving reproduction, teratogenesis, or carcinogenesis. Fd Cosmet Toxicol 8: 177–182.CrossRefGoogle Scholar
  32. Williams DA (1975) The analysis of binary responses from toxicological experiments involving reproduction and teratogenicity. Biom 31: 949–952.Google Scholar
  33. Williams DA (1982) Extra-binomial variation in logistic linear models. Appl Statist 31: 144–148.CrossRefGoogle Scholar
  34. Williams DA (1988) Estimation bias using the beta-binomial distribution in teratology. Biom 44: 305–309.Google Scholar
  35. Zegar SL, Liang KY, Albert PS (1988) Models for longitudinal data: A generalized estimating equation approach. Biom 44: 1049–1060.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1992

Authors and Affiliations

  • R. Woodrow Setzer

There are no affiliations available

Personalised recommendations