The reproducibility crisis is driven, in part, by invalid statistical analyses that are from data-driven hypotheses.
Nevertheless, scientists see some progress on the problem of reproducibility.
New research predicts that audits would reduce the number of false positive results from 30.2 per 100 papers to 12.3 per 100.
Political activism for science is fine as long as science itself remains trustworthy.
Polite entrenchment, at least in one recent case.
Do classic psychological studies published in high-profile journals hold up? The Reproducibility Project aims to find out.