The purpose of this project is to conduct research in statistical methods and computer techniques with particular emphasis on those appropriate for analyzing data from clinical, diagnostic, and prevention trials and epidemiologic studies of cancer. Many of the problems studied under this project arise from the consultative activities of the Section. Important activities during the past year have included evaluation and application of methodology for the analysis of highly correlated dietary variables as risk factors for cancer, as well as accounting for the effect of measurement error (including correlated errors) and intra-individual variation in dietary data; studying approaches to doubly sampled survival data with informative censoring: and assessing power gains from matching on predictor variables in intervention studies, with emphasis on designs involving randomization of matched pairs of communities. Previous work on an interactive computer program for calculating sample size has continued. Finally, the Section has continued to maintain and improve software for interactive analysis of complex medical data using sophisticated multiple regression techniques and survival analysis.
