,
5 tweets,
1 min read
Read on Twitter
Hmm interesting question.
My take on cause of/lesson of replicability/p-hacking issues:
Classic motivated reasoning
People have strong incentive to 1) cheat, but to do so in ways that are 2) culturally acceptable and 2) plausibly deniable. AND to 3) avoid self-reflection
No?
My take on cause of/lesson of replicability/p-hacking issues:
Classic motivated reasoning
People have strong incentive to 1) cheat, but to do so in ways that are 2) culturally acceptable and 2) plausibly deniable. AND to 3) avoid self-reflection
No?
(Thus replicability issue doesn’t say *much* about the individual (albeit is clearly a moral hazard component and individual differences to susceptibility therein), but about problems w/ institutional incentives+human nature.)
(And moral hazard component is quite hard to detect/penalize. Partly because so much is unobservable. But also even when confident the researcher was iffy, are huge incentives not to call out if not sure/others don’t agree. Hence why plausible deniability so useful.)
(Which raises interesting/important question: how do we better design institutional incentives to get rid of such plausible deniability. And make the substandard methods more observable? Or give people are stronger motive for long term impact/truth finding and less for pizzazz?)
(Problem is also not just with original authors. But with editors, referees, & hiring/promotion committeees who ALSO aren’t incentivized (enough) to care bout long term truth/impact. A *huge* problem w/ modern academic institutions imho. —> perverse incentives among researchers.)
