Pop science: 'P-hacking' goes mainstream

I was surprised to read that the term ‘p-hacking’ was founded by Simonsohn et al in 2012. I thought it had occurred among statisticians before that? Regardless, it is indeed a useful term.

2 Likes

Interesting article! I do not quite agree though with the fact that “p-hacking” is unintentional. In my personal experience I have observed many instances of “p-hacking” that were performed despite the awareness that this would contradict basic epistemological rules.

We must remember that scientists engage in “p-hacking” not only because of “the human tendency to seek and preferentially find evidence that confirms what we’d like to believe” (which by the way should be carefully taken into account and scrutinized when engaging in scientific research), but ESPECIALLY because “Journals generally prefer to publish statistically significant results, so scientists have incentives to select ways of parsing and analyzing their data that produce a p-value under 0.05” and most importantly (Wired forgot to mention it), scientists get funds, positions, merit based on how many high-impact articles they publish…

4 Likes