“The Stippling Shows Statistically Significant Grid Points”: How Research Results are Routinely Overstated and Overinterpreted, and What to Do about It

By D. Wilks. 2016

692 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Agricultural Drought Prediction Based on Conditional Distributions of Vine Copulas (2021, methodology): “Figure 3 shows the 1–2-months lag Kendall correlation coefficient (τk) (the false discovery rate (FDR; Wilks, 2016) procedure is used to correct τk at a 0.”
Testing for differences between two distributions in the presence of serial correlation using the Kolmogorov–Smirnov and Kuiper's tests (2021, background): “…should be noted that although this work deals only with the effects of temporal coherence, once local (e.g., gridpoint or station) significance has been established by appropriate means, recent advances allow for addressing the problem of spatial coherence in a straightforward manner (Wilks, 2016).”
Neural networks for post-processing ensemble weather forecasts (2018, methodology): “Following suggestions of Wilks (2016) we apply a Benjamini and Hochberg (1995) procedure to control the false discovery rate at level α .”