I wanted to say: “Ben, I think you may be misunderstanding what I meant, I clarified to Sanjay here: https://twitter.com/irisvanrooij/status/1063677813495083009?s=21 …” but then I saw that IS the tweet you responded to. Was I so unclear?
-
-
Replying to @IrisVanRooij @hardsci
No. I just disagree that it’s useful to characterise it as a distraction.
1 reply 0 retweets 0 likes -
Disagreement requires mutual understanding I think, but OK.
1 reply 0 retweets 1 like -
Replying to @IrisVanRooij @hardsci
I think I understand you just fine. My point is that it’s people arguing that improvement of hypothesis testing etc is unnecessary that are stopping the focus shifting to harder fixes like theory construction. Thats the distraction. That’s all.
1 reply 0 retweets 0 likes -
Who argues that?
1 reply 0 retweets 1 like -
Replying to @IrisVanRooij @hardsci
Ben Jones Retweeted Gordon Pennycook
Stuff like this is still puzzling common.https://twitter.com/gordpennycook/status/1063525312166690816?s=21 …
Ben Jones added,
Gordon Pennycook @GordPennycookRichard Shiffrin just gave a talk at#psynom18 and argued against the utility of preregistration. Started by confusing preregistration with registered reports. Then went on to argue that "science is posthoc" (and, presumably, should be). Oy pic.twitter.com/d2vVPX1DODShow this thread1 reply 0 retweets 0 likes -
Iris van Rooij Retweeted Richard D. Morey
I found
@richarddmorey’s thread helpful and insightful as it shows how positions such as by Schiffrin and Van Zandt may have reasonable interpretations.https://twitter.com/richarddmorey/status/1063837679517872129?s=21 …Iris van Rooij added,
Richard D. Morey @richarddmoreyReplying to @richarddmorey @tmalsburg @dstephenlindsayThis is not to say that pre-registration of things like experimental design is not important -- it is. But there are many areas (e.g., statistical modelling, Van Zandt's area) where I think pre-registration is not as useful. Disc. of her talk should keep that context in mind.1 reply 0 retweets 3 likes -
Replying to @IrisVanRooij @Ben_C_J and
Iris van Rooij Retweeted Joshua Skewes
Also much appreciated
@JCSkewesDK ‘s angle:https://twitter.com/jcskewesdk/status/1063880446549913602?s=21 …Iris van Rooij added,
Joshua Skewes @JCSkewesDKReplying to @JCSkewesDK @IrisVanRooij and 2 othersPre-reg is only essential to progress in the first relation. Claiming that pre-reg is essential to progress in ALL behavioural science is implicitly arguing that all behavioral science is Carnapian experimental psych. This is why modelers might feel slighted by the claim.1 reply 0 retweets 2 likes -
Replying to @IrisVanRooij @hardsci and
I agree with many of those points, but I just don’t see how any of them make the claim that ‘Scientists should make decisions about whether or not to publish a study based on their results’ (from the slide) defensible.
2 replies 0 retweets 0 likes -
Replying to @Ben_C_J @IrisVanRooij and
For modellers, you publish a study on the basis of thereotical norms moreso than results, so no problem there. What a modeller might disagree with is that pre-registration or even replication is necessary for progress.
1 reply 2 retweets 3 likes
Not sure if there's a good point in these subthreads to say this but thank you, @IrisVanRooij @richarddmorey @JCSkewesDK. As a more junior person seeing you explaining & defending modeling & showing why pre-reg doesn't really make sense for modeling, I'm so happy to not be alone.
-
-
Thanks Olivia! (Though I'm of course less experienced than you in all this.)
0 replies 0 retweets 2 likesThanks. Twitter will use this to make your timeline better. UndoUndo
-
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.