Meta-analysis: the fashion of summing-up evidence. Part I. Rationale and conduct.

Meta-analysis is the process of formally combining the quantitative results of separate studies in order to increase the statistical precession of estimated effects. It has become fashionable when individual studies fail to yield conclusive results. A recent update of a meta-analysis (overview) for treatments of patients with early breast cancer motivated this commentary to discuss the rationale, principles of conduct, statistical methods, and graphical display for summing up results. In part II we will approach the issue of interpretation and use of overview data.

[1]  M. Dowsett,et al.  How does tamoxifen interact with chemotherapy? , 1991, The Lancet.

[2]  C. Mann.  Meta-analysis in the breech. , 1990, Science.

[3]  C. Meinert.  Meta-analysis: science or religion? , 1989, Controlled clinical trials.

[4]  K. Wachter,et al.  Disturbed by meta-analysis? , 1988, Science.

[5]  Jack Cuzick,et al.  Effects of adjuvant tamoxifen and of cytotoxic therapy on mortality in early breast cancer. An overview of 61 randomized trials among 28,896 women , 1988 .

[6]  R. Light.  Accumulating evidence from independent studies: what we can win and what we can lose. , 1987, Statistics in medicine.

[7]  D L Demets,et al.  Methods for combining randomized clinical trials: strengths and limitations. , 1987, Statistics in medicine.

[8]  T. Chalmers,et al.  Meta-analyses of randomized controlled trials. , 1987, The New England journal of medicine.

[9]  R. Gelber,et al.  The concept of an overview of cancer clinical trials with special emphasis on early breast cancer. , 1986, Journal of clinical oncology : official journal of the American Society of Clinical Oncology.

[10]  R. Simes.  Publication bias: the case for an international registry of clinical trials. , 1986, Journal of clinical oncology : official journal of the American Society of Clinical Oncology.

[11]  R. Gelber,et al.  Adjuvant chemotherapy for breast cancer. A pooled estimate based on published randomized control trials. , 1986, JAMA.

[12]  N. Laird,et al.  Meta-analysis in clinical trials. , 1986, Controlled clinical trials.

[13]  A Liberati,et al.  A quality assessment of randomized control trials of primary treatment of breast cancer. , 1986, Journal of clinical oncology : official journal of the American Society of Clinical Oncology.

[14]  T A Louis,et al.  Findings for public health from meta-analyses. , 1985, Annual review of public health.

[15]  U. Bertazzoni,et al.  Philadelphia chromosome and TdT-positive AML. , 1984, Journal of clinical oncology : official journal of the American Society of Clinical Oncology.

[16]  Jeffrey E. Harris,et al.  Bayes Methods for Combining the Results of Cancer Studies in Humans and other Species , 1983 .

[17]  L. Freedman.  Tables of the number of patients required in clinical trials using the logrank test. , 1982, Statistics in medicine.

[18]  R. Rosenthal.  The file drawer problem and tolerance for null results , 1979 .

[19]  L Goldman,et al.  Anticoagulants and myocardial infarction. The problems of pooling, drowning, and floating. , 1979, Annals of internal medicine.

[20]  T C Chalmers,et al.  The importance of beta, the type II error and sample size in the design and interpretation of the randomized control trial. Survey of 71 "negative" trials. , 1978, The New England journal of medicine.

[21]  R. Rosenthal.  Combining results of independent studies. , 1978 .

[22]  M. Pike,et al.  Design and analysis of randomized clinical trials requiring prolonged observation of each patient. II. analysis and examples. , 1977, British Journal of Cancer.

[23]  G. Glass.  Primary, Secondary, and Meta-Analysis of Research1 , 1976 .

[24]  W. Haenszel,et al.  Statistical aspects of the analysis of data from retrospective studies of disease. , 1959, Journal of the National Cancer Institute.

[25]  W. G. Cochran.  Problems arising in the analysis of a series of similar experiments , 1937 .