lol
-
-
And yes, of course I know Rich Shiffrin. His views will represent many in the math psych community.
-
Same here, Rich is a well known figure in the field. I read his remarks as saying that there is an economy of trust in science and this seems obviously true. Pre-reg will not eliminate this economy either.
-
pre-registrations aren't intended to eliminate that economy, they are intended to help it function better. sort of like how regulating the rest of the economy is supposed to work too!
-
Depends on your definition of better though. Increased thresholds for signal detection reduce the hit rate as well as reducing false alarms. That's one of Rich's points IIRC.
-
No reason for it to reduce hit rate. It just means your serendipitous "hit" isn't allowed to masquerade as a hypothesis test or confidence interval.
-
I joined this thread with a joke, but seeing some earnest defenders of Shiffrin on here, I read his Psychonomic Society blog. And, I have to say, I find it appalling. I would say slippery.
-
His starting point is the exploratory nature of scientific research. Well and good, and a reason not everything can or should be pre-registered. But he rejects any line between that exploration & either testing or (as he prefers) estimation.
-
As a general thing, with no such line, if the papers he is talking about report p values or confidence intervals without being extremely clear about every step of the process that got them there, then they are lies.
- 13 more replies
New conversation -
-
-
Airing these views, which appear to include the claim that there's no major harm from a system in which scientific publications mislead and misstate, does indeed probably have a negative influence on your field if as a result you all think that's ok for you to do as well.
-
but since he's presumably powerful and he is also probably acting on these views anyway it does have a good effect to see them out in the open and understand what people really think, so in that way it does help outline the situation.
-
Last time I checked it's more than 150 journals in psych that take RRs. So obviously, it's a thing that's catching on.
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.
)