Standard Article

Meta-Analysis in Epidemiology

  1. Donna F. Stroup1,
  2. Stephen B. Thacker2

Published Online: 15 JUL 2005

DOI: 10.1002/0470011815.b2a03083

Encyclopedia of Biostatistics

Encyclopedia of Biostatistics

How to Cite

Stroup, D. F. and Thacker, S. B. 2005. Meta-Analysis in Epidemiology. Encyclopedia of Biostatistics. 5.

Author Information

  1. 1

    National Center for Chronic Disease Prevention & Health Promotion, Atlanta, GA, USA

  2. 2

    National Center for Chronic Disease Prevention and Health Promotion, Atlanta, GA, USA

Publication History

  1. Published Online: 15 JUL 2005

Abstract

Meta-analysis is a quantitative approach for systematically combining the results of previous research in order to arrive at conclusions about the body of research. The pressure for timely, evidence-based decisions, and the explosion of the information in the scientific literature have resulted in an increased number of published meta-analysis. Statistical methods are integral to each step of a meta-analysis. In this chapter, we define meta-analysis in the context of scientific synthesis, illustrate uses of Meta-analysis in epidemiology and public health, describe the steps in a meta-analysis, and illustrate some specific statistical issues, such as bias, and heterogeneity. We illustrate these steps with a case study of the effects of duration of estrogen on breast cancer risk and discuss statistical software and related internet resources. Statistical issues are critical to properly understanding and interpreting the results from meta-analysis.

Keywords:

  • statistical synthesis;
  • bias;
  • heterogeneity;
  • review;
  • evidence;
  • policy