Original article
Meta-analysis in epidemiology, with special reference to studies of the association between exposure to environmental tobacco smoke and lung cancer: A critique

https://doi.org/10.1016/0895-4356(91)90261-7Get rights and content

Abstract

Meta-analysis, a set of statistical tools for combining and integrating the results of independent studies of a given scientific issue, can be useful when the stringent conditions under which such integration is valid are met. In this report we point out the difficulties in obtaining sound meta-analyses of either controlled clinical trials or epidemiological studies. We demonstrate that hastily or improperly designed meta-analyses can lead to results that may not be scientifically valid. We note that much care is typically taken when meta-analysis is applied to the results of clinilcal trials. The Food and Drug Administration, for example, requires strict adherence to the principles we discuss in this paper before it allows a drug's sponsor to use a meta-analysis of separate clinical studies in support of a New Drug Application.

Such care does not always carry over to epidemiological studies, as demonstrated by the 1986 report of the National Research Council concerning the purported association between exposure to environmental tobacco smoke and the risk of lung cancer. On the basis of a meta-analysis of 13 studies, 10 of which were retrospective and the remaining 3 prospective in nature, the Council concluded that non-smokers who are exposed to environmental tobacco smoke are at greater risk of acquiring lung cancer than non-smokers not so exposed. In our opinion, this conclusion in unwarranted given the poor quality of the studies on which it is based.

References (63)

  • T.C. Chalmers et al.

    Meta-analysis of clinical trials as a scientific discipline. I. Control of bias and comparison with large co-operative trials

    Stat Med

    (1987)
  • K. O'Rourke et al.

    Meta-analysis in medical research: Strong encouragement for higher quality individual research efforts

    J Clin Epidemiol

    (1989)
  • R. Peto

    Why do we need overviews of randomized trials

    Stat Med

    (1987)
  • S.J. Pocock

    Clinical Trials: A Practical Approach

  • S. Yusuf

    Obtaining medically meaningful answers from an overview of randomized clinical trials

    Stat Med

    (1987)
  • E.A. Gehan et al.

    Non-randomized controls in cancer clinlical trials

    N Engl J Med

    (1974)
  • R.J. Light

    Accumulating evidence from independent studies: What we can win and what we can lose

    Stat Med

    (1987)
  • L.V. Hedges

    Commentary

    Stat Med

    (1987)
  • H.J. Eysenck

    An exercise in mega-silliness

    Am Psychol

    (1978)
  • J.A. Berlin et al.

    A meta-analysis of physical activity in the prevention of coronary heart disease

    Am J Epidemiol.

    (1990)
  • G.V. Glass et al.

    Meta analysis in social research

  • M. Smith et al.

    The Benefits of Psychotherapy

  • S. Iyengar et al.

    Selection models and the file drawer problem

    Stat Sci

    (1988)
  • J.A. Berlin et al.

    An assessment of publication bias using a sample of published clinical trials

    J Am Stat Assoc

    (1989)
  • S. Dubey

    Regulatory considerations on meta-analysis, dentifrice studies and multicenter trials

  • R.A. Stein

    Meta-analysis from one FDA reviewer's perspective

  • J.L. Fleiss

    The Design and Analysis of Clinical Experiments

  • J.L. Fleiss

    Statistical Methods for Rates and Proportions

  • D.L. DeMets

    Methods for combining randomized clinical trials: Strengths and limitations

  • M.J. Stampfer et al.

    Effect of intravenous streptokinase on acute myocardial infarction. Pooled results from randomized trials

    N EngI J Med

    (1982)
  • The effect of diltiazem on mortality and reinfarction after myocardial infarction

    N Engl J Med

    (1988)
  • Cited by (0)

    View full text