The statistical significance filter leads to overoptimistic expectations of replicability

• Published in: Journal of memory and language 2018-12, Vol.103, p.151-175
• Main Authors: Vasishth, Shravan, Mertzen, Daniela, Jäger, Lena A., Gelman, Andrew
• Format: Article
• Language: English
• Subjects: Bayesian data analysis; Expectation; Locality; Parameter estimation; Replicability; Surprisal; Type M error
• ISSN: 0749-596X; 1096-0821
• DOI: 10.1016/j.jml.2018.07.004

•When low-powered studies show significant effects, these will be overestimates.•Significant effects from low-powered studies will not be replicable.•Seven experiments show that effects reported in Levy and Keller (2013) are not replicable.•Relying only on statistical significance leads to overconfident expectations of replicability.•We make several suggestions for improving current practices. It is well-known in statistics (e.g., Gelman & Carlin, 2014) that treating a result as publishable just because the p-value is less than 0.05 leads to overoptimistic expectations of replicability. These effects get published, leading to an overconfident belief in replicability. We demonstrate the adverse consequences of this statistical significance filter by conducting seven direct replication attempts (268 participants in total) of a recent paper (Levy & Keller, 2013). We show that the published claims are so noisy that even non-significant results are fully compatible with them. We also demonstrate the contrast between such small-sample studies and a larger-sample study; the latter generally yields a less noisy estimate but also a smaller effect magnitude, which looks less compelling but is more realistic. We reiterate several suggestions from the methodology literature for improving current practices.