Despite decades of warnings, many areas of science still insist on labelling a result of P < 0.05 as “significant”. In this article, D. Colquhoun discusses whether the inconsiderate use of p-values and other questionable research practices like multiple comparisons, lack of randomisation and P-hacking account for a substantial part of the reproducibility issue. He concludes that science is endangered by statistical misunderstanding, and by people who impose perverse incentives on scientists.

LINK