Meta-analysis and power: some suggestions for the use of power in research synthesis

The importance of statistical power is under recognized both in single study research and meta-analysis. The power of a study is the probability that it will lead to a statistically significant result. A simple method of establishing the adequacy of the power of meta-analysis is suggested and examples from 2 meta-analytic studies that may have produced inaccurate results are provided. Suggestions are made for changes in the protocol of meta-analytic studies that highlight the importance of power analysis