ISPO

Published in Cancer Detection and Prevention 1999; 23(2):97-106.

Understanding Meta-Analysis in Cancer Epidemiology: Dietary Fat and Breast Cancer

Renée A. Harrison, Ph.D.a, and John W. Waterbor, M.D., Dr.PH.b

a Biostatistics Unit, Comprehensive Cancer Center, and b Department of Epidemiology, University of Alabama at Birmingham, Birmingham, AL

Address all correspondence and reprint requests to: Renée A. Harrison, Ph.D., WTI 153, 1824 Sixth Avenue South, Birmingham, AL 35294-3300.

ABSTRACT: Meta-analyses of the relationship between dietary fat and breast cancer risk using different methodologies have reported conflicting results. This investigation compares methodologic aspects of metaanalyses of patient data (MAP) with metaanalyses of data from the literature (MAL), and computes relative risk (RR) estimates from a random effects model using 28 published studies of dietary fat and breast cancer. MAP and MAL results compare closely when homogeneity is verified. When statistical homogeneity is rejected, a random effects model adjusting for study design and location is appropriate. The highest RR was found for case-control studies of European women (RR: 1.46), followed by North American case-control studies (RR: 1.25), case-control studies of women on other continents (RR: 1.23), cohort studies in Europe (RR: 1.20), and cohort studies in North America (RR: 1.02). The overall risk estimate in a MAL with heterogeneous studies should be interpreted only in a conditional model.

KEY WORDS: cancer epidemiology, epidemiologic methods, random effects regression, regression models.

For more information, contact harrison@cirrus.biosccc.uab.edu

http://www.cancerprev.org/Journal/Issues/23/2/312