P values, the ‘gold standard’ of statistical validity, are not as reliable as many scientists assume.
A feature article in Nature about p-values. Read it here.
For kicks you might enjoy checking out what other people are saying about this piece, via Altmetric.
Also check out the graphic on p-value calibration: If your p-value is 0.05 and your prior odds are 50:50, what is the minimum posterior probability for the null? (Spoiler alert: the answer probably isn’t what you’d think. Unless you’ve see this graphic before, that is.) Click on the graphic