DESCRIPTION (Adapted from applicant's abstract): Society depends on the
science of quantitative risk assessment for protection against environmental
exposures that can cause cancer, impaired reproductive health and other
adverse health effects. Due to limitations and availability of reliable
epidemiological information, controlled experiments in laboratory animals
continue to play an important role in the risk assessment process. the
important and high cost of these studies warrant continued statistical
research to ensure that the best design and analysis techniques are being
used.
This is a proposal to address a selection of statistical problems that arise
in the design and analysis of rodent carcinogenicity as well as
developmental and reproductive toxicity (teratology) experiments. the broad
aims are: 1. To evaluate and extend existing methods for fitting
three-state models for carcinogenicity data. 2. To extend and apply
empirical Bayes methods to incorporate various types of historical control
of methods to adjust for body weight in the analysis of tumor incidence
data. 3. to study statistical models for multiple outcomes that arise in
teratology studies. Empirical data analysis will play a central role in the
proposed research.
Error Notice
The database may currently be offline for maintenance and should be operational soon. If not, we have been notified of this error and will be reviewing it shortly.
We apologize for the inconvenience.
- The DCCPS Team.