In this PDF document, Jerry Brunner and I would like to share our latest manuscript on z-curve, a method that estimates average power of a set of studies selected for significance. We call this estimate replicabilty because average power determines the success rate if the set of original studies were replicated exactly.
We welcome all comments and criticism as we plan to submit this manuscript to a peer-reviewed journal by December 1.
Comparison of P-curve and Z-Curve in Simulation studies
Estimate of average replicability in Cuddy et al.’s (2017) P-curve analysis of power posing with z-curve (30% for z-curve vs. 44% for p-curvce).
Estimating average replicability in psychology based on over 500,000 significant test statitics.
Comparing automated extraction of test statistics and focal hypothesis tests using Motyl et al.’s (2016) replicability analysis of social psychology.