The focus of this project is development and refinement of statistical procedures for the design and analysis of cancer screening and related studies. Statistical problems under investigation include sample size determination, development and comparison of data analysis methods, and development of monitoring procedures for screening trials. Each of these problem areas is common to screening and prevention trials in which the Division participates, but the methods for screening studies must address the special lead time and length biases inherent in screening programs. A procedure based on a statistical test for paired data has been developed to determine the samples size required when comparing the sensitivity of two screening tests in the situation where both tests are performed on a group of subjects and individuals positive on either test received a diagnostic workup. Survival data of breast cancer cases in the HIP study were analyzed using competing risk theory to determine if screening produced delay or elimination of mortality. It was concluded that some breast cancer cases detected by screeening realized a cure. Research into stopping procedures for screening trials uses cost-benefit methodology to determine whether to stop or continue a study. A Baysian approach for updating information at successive points in time is utilized. Models of disease and screening are being developed to aid in the interpretation and monitoring of colon cancer screening programs. Properties of case-control studies in the context of screening evaluation are also being considered. Alternative definitions of cases, controls, and exposure periods will be analyzed.
