Tests for evidential value and p-hacking across disciplines, using <i>p</i>-values obtained from the Results section.

Number of p-values in each bin is the mean number based on 1,000 bootstraps of one p-value per Results section, rounded to the nearest whole number. Disciplines (n = 8) for which we found fewer than 50 p-values below 0.05 in the Results section were excluded. Tests for evidential value and p-hacking across disciplines, using p-values obtained from the Results section.