A Three-state Multiplicative Model for Rodent Tumorigenicity Experiments

SUMMARY A three-state illness-death model provides a useful way to represent data from rodent tumorigenicity experiments. Some of the earliest proposals use fully parametric models based on, for example, Weibull distributional assumptions. Recently, nonparametric versions of this model have been proposed, but these generally require large data sets with frequent interim sacrifices to yield stable estimates. As a compromise between these extremes, others have considered semiparametric models. In this paper, we develop a model that assumes a multiplicative relationship between death rates with and without tumour and a piecewise exponential model for the base-line transition rates. The model can be fitted with information from a single sacrifice. An EM algorithm provides a useful way to fit the model, since the likelihood corresponds to that from a standard piecewise exponential survival model when time to tumour onset is known. We discuss the relationship between the piecewise exponential model and other recent proposals and illustrate the method with data from two carcinogenicity studies.

[1]  R L Kodell,et al.  An illness-death model for the study of the carcinogenic process using survival/sacrifice data. , 1980, Biometrics.

[2]  R Peto,et al.  Editorial: Guidelines on the analysis of tumour rates and death rates in experimental animals. , 1974, British Journal of Cancer.

[3]  Stephen W. Lagakos,et al.  On the Representativeness Assumption in Prevalence Tests of Carcinogenicity , 1985 .

[4]  Gregg E. Dinse,et al.  Simple Parametric Analysis of Animal Tumorigenicity Data , 1988 .

[5]  L. Ryan,et al.  On the use of covariates for rodent bioassay and screening experiments , 1988 .

[6]  J Cuzick,et al.  A review of semi-parametric models for life histories. , 1984, IMA journal of mathematics applied in medicine and biology.

[7]  J D Kalbfleisch,et al.  Nonparametric methods for survival/sacrifice experiments. , 1986, Biometrics.

[8]  T. J. Mitchell,et al.  Log-linear models in the analysis of disease prevalence data from survival/sacrifice experiments. , 1979, Biometrics.

[9]  D. Cox,et al.  Analysis of Survival Data. , 1985 .

[10]  N. E. Breslow.  Statistical Methods in Cancer Research , 1986 .

[11]  J P Klein,et al.  A biological marker model for predicting disease transitions. , 1984, Biometrics.

[12]  Louise Ryan,et al.  On the role of cause-of-death data in the analysis of rodent tumorigenicity experiments , 1989 .

[13]  Gregg E. Dinse,et al.  Regression Analysis of Tumour Prevalence Data , 1983 .

[14]  S W Lagakos,et al.  Nonparametric estimation of lifetime and disease onset distributions from incomplete observations. , 1982, Biometrics.

[15]  Xiao-Li Meng,et al.  Using EM to Obtain Asymptotic Variance-Covariance Matrices: The SEM Algorithm , 1991 .

[16]  Gregg E. Dinse.  A Prevalence Analysis that Adjusts for Survival and Tumour Lethality , 1988 .

[17]  G. Dinse.  Constant risk differences in the analysis of animal tumorigenicity data. , 1991, Biometrics.

[18]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[19]  J Wahrendorf,et al.  Guidelines for simple, sensitive significance tests for carcinogenic effects in long-term animal experiments. , 1980, IARC monographs on the evaluation of the carcinogenic risk of chemicals to humans. Supplement.

[20]  Gregg E. Dinse,et al.  Nonparametric prevalence and mortality estimators for animal experiments with incomplete cause-of-death data , 1986 .

[21]  M. Friedman.  Piecewise Exponential Models for Survival Data with Covariates , 1982 .

[22]  C. Portier.  Estimating the tumour onset distribution in animal carcinogenesis experiments , 1986 .

[23]  R. Kay.  The analysis of transition times in multistate stochastic processes using proportional hazard regression models , 1982 .

[24]  Nan M. Laird,et al.  Covariance Analysis of Censored Survival Data Using Log-Linear Analysis Techniques , 1981 .

[25]  Comparison of Two Treatments in Animal Carcinogenicity Experiments , 1988 .

[26]  K. Liestøl,et al.  Efficiencies of experimental designs for an illness-death model. , 1984, Biometrics.

[27]  D G Hoel,et al.  Statistical analysis of survival experiments. , 1972, Journal of the National Cancer Institute.

[28]  R L Kodell,et al.  Nonparametric joint estimators for disease resistance and survival functions in survival/sacrifice experiments. , 1982, Biometrics.

[29]  C J Portier,et al.  Semiparametric analysis of tumor incidence rates in survival/sacrifice experiments. , 1987, Biometrics.

[30]  Niels Keiding,et al.  Non- and semi-parametric estimation of transition probabilities from censored observation of a non-homogeneous Markov process , 1991 .

[31]  T. Louis,et al.  Use of Tumour Lethality to Interpret Tumorigenicity Experiments Lacking Cause‐Of‐Death Data , 1988 .

[32]  T. Louis.  Finding the Observed Information Matrix When Using the EM Algorithm , 1982 .

[33]  Barbara McKnight,et al.  Tests for differences in tumor incidence based on animal carcinogenesis experiments , 1984 .

[34]  G. Dinse.  Estimating tumor incidence rates in animal carcinogenicity experiments. , 1988, Biometrics.

[35]  T. J. Mitchell,et al.  Nonparametric estimation of the distribution of time to onset for specific diseases in survival/sacrifice experiments. , 1984, Biometrics.

[36]  D. Rubin,et al.  Statistical Analysis with Missing Data. , 1989 .