Grant Number:	5P01CA053996-27 Interpret this number
Primary Investigator:	Prentice, Ross
Organization:	Fred Hutchinson Cancer Research Center
Project Title:	Statistical Methods for Medical Studies
Fiscal Year:	2004

The aim of this competing renewal is the development of statistical methods for biomedical research, with an emphasis on procedures and tools needed in chronic disease population research. The ultimate goal of chronic disease population research is the development of practical interventions that can reduce the risk of prominent cancers and vascular diseases, among other diseases, that impose a major burden on the US and other populations. Project 1 is concerned with certain issues that limit the ability to identify the behavioral or chemopreventive interventions that merit clinical trial testing, and with methods needed for informative benefit versus risk assessment in prevention clinical trials. These include topics in multi-variate failure time analysis; methods for measurement error accommodation; and comparison of the reliability of various study designs. Project 2 is concerned with genetic/genomic data analysis. It will focus on the methods to relate and characterize genotypes for a possibly large number of functional genes, or coding polymorphisms within genes, to disease risk in the context of family studies. Specific topics include disease-related gene identification; multiple testing issues and methods for the assessment of gene-environment interactions. Project 3 is concerned with statistical methods for biomarker research, particularly as related to the early detection of disease, and with the methods for design and analysis of group randomized trials, as frequently arise in community-based approaches to risk factor modification. A range of mathematical modeling and statistical estimation techniques will be used to address project aims. Evaluation of new methods will include asymptomatic distribution theory development whenever practical, along with computer simulations and applications to pertinent real data sets. Collectively these projects will address statistical topics that are among the most important for progress in chronic disease population research, by applying the talents of a highly committed and interactive group of statistical and mathematical scientists.





None