A survival-adjusted quantal-response test for analysis of tumor incidence rates in animal carcinogenicity studies

In rodent cancer bioassays, groups of animals are exposed to different doses of a chemical of interest and followed for tumor occurrence. The resulting tumor rates are commonly analyzed using a survival-adjusted Cochran-Armitage (CA) trend test. The CA trend test has reasonable power when the tumor-response curve is linear in dose, but it may be underpowered for a nonlinear response. An alternative survival-adjusted test procedure based on isotonic regression methodology has previously been proposed. Although this alternative procedure performs well when the tumor response is nonlinear in dose, it has less power than the CA trend test when the response is linear in dose. Here, we introduce a new survival-adjusted test procedure that makes use of both the CA trend test and the isotonic regression-based trend test. Using a broad range of experimental conditions typical of National Toxicology Program (NTP) bioassays, we conducted extensive computer simulations to compare the false-positive error rate and power of the proposed procedure with the survival-adjusted CA trend test. The new procedure competes well with the survival-adjusted CA trend test when observed tumor rates are linear in dose and performs substantially better when observed tumor rates are nonlinear in dose. Further, the proposed trend test almost always has a smaller false-positive rate than does the survival-adjusted CA trend test. We also developed an order-restricted inference-based procedure for performing multiple pairwise comparisons between each of the dose groups and the control group. The trend test and the multiple pairwise comparisons test are demonstrated using an example from a study conducted by the NTP.