Reproducibility in the absence of selective reporting: An illustration from large-scale brain asymmetry research.

For an effect that was significant at p ≤ .05 in a given meta‐analysis of 98 datasets (or more stringently at p ≤ .05/70 to correct for multiple comparisons across 70 effects), the effect in the remaining single dataset would need to be in the same left–right direction as in the meta‐analysis, and also be nominally significant within the single dataset ( p ≤ .05), in order to be counted as reproduced in that dataset.

also in 7,732 other papers