There is no accepted minimum number of studies that are required for a meta-analysis. However, in different refernces you can find different minimum number of studies. For example:

• Cochrane handbook: a minimum of 10 studies

(no reason for the number)

• At least 6-10 studies for a continuous study-level

variable when the sizes of the included studies

are moderate or large (Fu et al., 2011)

• For a categorical subgroup variable, each

subgroup should have a minimum of 4 studies (Fu

et al., 2011)

Thank you very much dears, this is very helpful indeed.

Two is minimum, but the more complete answer lies in understanding the power of the statistical tests in meta-analysis.

Good Luck ...

Ninan, I also have your concern, trying to do a subgroup meta-analysis. Would you share with us your conclusions?

Ali

In order to do subgroup analysis there should be enough number of studies of at least 10 or so. If your data doesn't meet this condition then you don't have to do this test.  Just describe and discuss the meta-analysis.

at least 10 in total, or 10 for each subgroup?

10 studies for each group

For sub-group analysis, we must consider the covariate distribution because it may affect the outcome in a study. In addition, a covariate can be an independent variable or it can be an unwanted, confounding variable. Adding a covariate to a model can increase the accuracy of your results.

On account of this criteria, the review author is required to consider the number of studies and participants to each sub-group. The Cochrane handbook advises that it is unlikely that an investigation of heterogeneity will produce useful findings unless there are at least 10 trials included in the meta-analysis, although 10 trials may be too few if the covariate is unevenly distributed.

Thanks.

At least 4 studies