Pre-registration formalizes Type 1 error rate control in hypothesis tests. That is all. With increasing adoption, one consequence is we will see an increase in people who realize they were not testing a hypothesis at all. That is progress.
-
-
So yeah, for a "no journals" science, see compsci, I guess? They haven't had journals since ever. They just do preprints and proceedings. Is that useful for you?
-
Compsci is a great example. The parts of psychology that are closer to compsci (e.g., that are testing computation models or using a data-driven approach) aren't well-served by either RRs or the journal-based publication model in general.
-
Yes, obviously. Something I've been saying on Twitter for years.
-
The tweet of yours I linked to comes off as saying that publications should all be RRs? But like I said above and you just also repeated, you have changed your perspective since you posted that.
-
It's less that I've changed my perspective and more that I'm aware others don't find it obvious that the RR model mostly applies to research in a hypothesis-testing framework so I'm trying to be clearer.
-
Right. A shift in rhetoric. Like I said.
-
Either way you and others in this thread have slowly but surely lost loads of math psych people and/or modelers. I'm interested to see how this will continue as it's caused IMHO quite a deep rift. I was literally just saying the other day that the field seems to be splitting.
-
I just hired a modeller as a post-doc for the next 4 years.
- 1 more reply
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.