Some thoughts on recent psychology study upheavals https://www.vox.com/2018/6/13/17449118/stanford-prison-experiment-fraud-psychology-replication … Mostly this: "In science, the first demonstration of an idea often becomes the lasting one — both in pop culture and academia. But this isn’t how science is supposed to work at all! "
-
-
Reading yr
#ReplicationCrisis catalog.
Beyond p-scores, replication, and not burying null results, anyone considering “pre hoc” hacks to incentive structure? Idea: Have researchers submit detailed experimental designs to a supra-IRB (or mobile app, whatever) for their field... -
Once approved, Study A is assigned to Team B to carry out; as they await results, Team A is likewise matched via qualifications and est timeframe to conduct Study C, and so on. Team A gets first dibs on writing up Study A’s raw data...
-
But Team B is given room alongside any published paper to provide its own take—whether a one-line certification of the findings, minor methodological concerns/clarifications, or a total rejection of A’s interpretation as statistical sleight-of-hand or worse...
-
Sure academics will balk at losing control, but they also effectively double their chances of publishing, not perishing. Most important, cleaving empirical fact-finding from theory/design/interpretation finally brings society’s basic scientific method to social scientists...
-
It’s obvious for the same reason reputable journalists aren’t their own editors, smart developers hire separate architects and engineering firms, and lawyers who represent themselves have a fool—or, if the law’s as toothless as peer review, an incipient charlatan—for a client.
End of conversation
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.