Publication Bias in Meta-Analysis: Confidence Intervals for Rosenthal’s Fail-Safe Number
Table 4
95% one-sided confidence limits above which the estimated is significantly higher than , which is the rule of thumb suggested by Rosenthal [11]. represents the number of studies included in a meta-analysis. We choose the variance from a fixed number of studies when the are drawn from a half normal distribution HN(0, 1), as this performed best in the simulations.