Analyzing health surveys for cancer-related objectives

Large-scale health surveys conducted by government agencies record informat ion on a large number of health-related variables, We review the use of the se data for performing analyses that address cancer-related objectives. Aft er describing the conduct of a large-scale health survey (the third Nationa l Health and Nutrition Examination Survey [NHANES III]), we discuss some of the issues involved in analyzing data collected in such a survey. In parti cular, the use of sample weights in the analysis and the importance of acco unting for the complex survey design when estimating standard errors are di scussed. Six applications are then presented that involve the following: I) estimating demographic factors associated with snuff use, 2) estimating th e association of type of health insurance with the probability of receiving a digital rectal examination, 3) estimating the association of body iron s tores with the probability of later developing cancer, 3) estimating the ch anging rates of mammography screening in the United States between 1987 and 1992, 5) evaluating smoking and alcohol consumption as risk factors for di gestive cancer by use of a population-based, case-control study, and 6) eva luating a randomized community-intervention experiment to encourage smoking cessation. These applications use data from the National Health Interview Survey, the NHANES I Epidemiologic Followup Study, the 1986 National Mortal ity Followback Survey, and the Community Intervention Trial for Smoking Ces sation. The availability of public-use data files is discussed for surveys sponsored by the U.S. government that collect health-related information. W e demonstrate that statistical methods and computer software are available for analyzing public-use data files of surveys to address different types o f cancer-related objectives.