At present, the replicability-report is based on articles published from 1995 to 2015. During this time, SOCIAL COGNITION published 550 articles. The Replicability-Report is based on 450 articles that reported one or more t or F-test in the text (results reported in Figures or Tables are not included). The test-statistic was converted into z-scores to estimate post-hoc-power. The analysis is based on 5,331 z-scores in the range from 2 (just above the 1.96 criterion value for p < .05 (two-tailed) to 4.
Based on the distribution of z-scores in the range between 2 and 4, the average power for significant results in this range is estimated to be 55% with a homogeneous model, which is currently being used for the replicability ranking. The average power assuming heterogeneity is 46%. This estimate suggests that only half of the published results with z-scores in this range yield significant results in an exact replication study with the same sample size and power (results with z > 4 are expected to replicate with nearly 100%).
The same method was used to estimate power for individual years.
The results show a decreasing trend and the estimate for the current year is only 35%. This estimate could still increase as more articles from 2015 are being published. However, the replicability score for SOCIAL COGNITION is low and raises concerns about the replicability of results published in this journal. The same method produced a replicability score of 32% for social psychology results in the OSF-Reproducibilty Project. The actual rate of successful replications, including z-scores greater than 4, was 8% when sample size was held constant. Thus, the replicability score of 35% for articles published in 2015 in SOCIAL COGNITION suggests that few of the theoretically important results published in SOCIAL COGNITION would replicate in an actual replication study.