The focus of this project is development and refinement of statistical procedures for the design and analysis of cancer screening and related studies. Problems under investigation include derivation and comparison of data analysis methods, assessment of case-control studies for screening evaluation, development of models of cancer screening, and approaches to the analysis of categorical data. Properties of case-control studies in the context of screening evaluation are being considered. It was found that the odds ratio from a case control study comparing screened versus not screened individuals is subject to bias and may underestimate or overestimate the impact of screening. Extensions were derived for a stage shift cancer screening model which uses the number of cancers diagnosed by stage in screened and control groups to estimate the number of cases shifted to earlier stages by screening and the mortality impact. The model was used to investigate age-specific breast cancer mortality in the HIP study. Screening impact appeared to be restricted to stage one disease in women less than 50, but both stage two and one cancers were affected by screening in older women. A novel application of capture-recapture methodology was developed to estimate screening test sensitivity and preclinical sojourn time. The EM algorithm was used to estimate parameters while variances were obtained using the bootstrap. Regression models were devised to address two particular situations. The first is analysis of grouped survival data in the presence of possibly informative censoring. The new method requires fewer parametric assumptions for the joint distribution of censoring and failure times than previous approaches. The second is the analysis of screening trial data in which a lag period occurs before the effect takes place. The innovation here is a modification of the multiplicative hazard model used in survival analysis which allows for an arbitrary time until the beginning of the screening effect and accounts for the impact of covariates.
