in the publishing everything approach was 0.023, with = 0 in 45.6% of the simulations, and an average value of equal to 0.0023. Note that the average standard error is close to both the theoretically derived = 0.02236 and the 0.0222 reported by W&H. It can be shown that the expected value of the variance of the meta-analytic effect across simulations is equal to the expected value of the squared standard error of one meta-analysis, if both are calculated under the publish everything approach. The average standard error in the selective publishing approach was 0.051, with >0 in all simulations and an average value of equal to 0.085. Note that the standard error was more than 2.2 times as large in the selective publishing as in the publishing everything approach. To conclude, the estimate of population effect size is more precise under publishing everything than under selective publishing.
