One thing if conclusions end up wrong. Seems like another if the *evidence* in paper is misrepresented (by e.g. p hacking)
-
-
Replying to @richarddmorey @o_guest
So a correction would be more appropriate. But can't solve p-hacking in retrospect, regrettably.
1 reply 0 retweets 2 likes -
Doesn't p hacking constitute an "honest error" & author saying they p hacked is "clear evidence"? http://publicationethics.org/files/retraction%20guidelines.pdf …
3 replies 1 retweet 2 likes -
Replying to @richarddmorey @o_guest
want? Retract? What is self-report effect is reliable, which is also in these papers? Partial retract?
1 reply 0 retweets 0 likes -
Only argue that retraction *should* be on the table for cases like this. Arg. that this should be retracted is for others.
2 replies 0 retweets 2 likes -
Replying to @richarddmorey @o_guest
You are free to retract anything you want. Expecting or asking for it requires very good reasons.
2 replies 0 retweets 0 likes -
sure. And an author saying "this evidence is unreliable due to our methodological practices" seems like a good reason
1 reply 1 retweet 1 like -
Replying to @richarddmorey @o_guest
But if the effect is true, the practices don't matter because there is no Type 1 error. So how do we know?
2 replies 1 retweet 0 likes -
Science is about quality of evidence and argument, not conclusions. Practices always matter.
1 reply 3 retweets 4 likes -
Conclusions matter too. Remember true premises & arguments can lead to wrong conclusions.
2 replies 0 retweets 0 likes
In this case both were wrong because of p hacking so no diff really
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.