Hmmm. Isn't this very similar to the Ioannidis base rate argument? Also, we actually know that QRPs are rather widespread.
-
-
2 replies 0 retweets 1 like
-
Replying to @IrisVanRooij @EJWagenmakers and
I am not sure, did not read in depth, but possibly the argument is slightly different. It seems to me (on very quick scan) that Bird seems to argue not from QRPs, but from the source of hypotheses (theory or not, e.g.):
1 reply 0 retweets 0 likes -
Replying to @IrisVanRooij @EJWagenmakers and
"Hypotheses in clinical medicine and in psychology, as well as in other sciences, may come from sources other than a basic theory. Hypotheses may be suggested by the results of observational studies or even by unsystematic observations or the researcher’s intuition." >>
1 reply 2 retweets 3 likes -
Replying to @IrisVanRooij @EJWagenmakers and
"These are perfectly legitimate means of generating hypotheses. On the other hand, they are not means of generating hypotheses that give those hypotheses a high probability of truth. Indeed, some sources seem clearly liable to produce false hypotheses."
1 reply 0 retweets 3 likes -
Ioannidis does not make finer distinctions but does argue that many hypotheses that are put to the test are a priori unlikely.
1 reply 0 retweets 4 likes -
Replying to @EJWagenmakers @IrisVanRooij and
same do
@psmaldino and@rlmcelreath here: https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0136088 …. And Wilson and Wixted here: https://journals.sagepub.com/doi/pdf/10.1177/2515245918767122 ….1 reply 2 retweets 5 likes -
Replying to @LeoTiokhin @EJWagenmakers and
Thanks. I think Bird tries to improve upon the argument of Ioannidis: There is a footnote that reads: "For this reason we cannot use the conclusion of Ioannidis ([2005b]), that most published research findings (in biomedicine) are false, ..."
1 reply 0 retweets 1 like -
Replying to @IrisVanRooij @EJWagenmakers and
"... since he uses similar arguments to reach that conclusion. Indeed, Goodman and Greenland ([2007]) accuse Ioannidis of circular reasoning."
1 reply 0 retweets 2 likes -
Replying to @IrisVanRooij @EJWagenmakers and
I may need to read it more carefully, but PPV (ala Ioannidis) and PPRV (the paper you linked to) seem identical, and some qual. conclusions (increase prior probability; decrease alpha) to increase prob published finding true are identical also. Again, see Mcelreath/Smaldino Model
1 reply 0 retweets 1 like
Not sure it's a problem to have a few similar papers is it? I mean that's kind of the whole point of disseminating ideas across related fields, right?
-
-
Replying to @o_guest @IrisVanRooij and
Only a problem if* one tries to pass off some idea as novel/fundamentally different than another when it's in fact entirely derivative.
1 reply 0 retweets 0 likes -
-
Replying to @o_guest @EJWagenmakers and
Iris van Rooij Retweeted Iris van Rooij
Not sure. I did note this (see also EJ's response):https://twitter.com/IrisVanRooij/status/1084212219657838604 …
Iris van Rooij added,
Iris van Rooij @IrisVanRooijReplying to @IrisVanRooij @EJWagenmakers and 2 othersI am not sure, did not read in depth, but possibly the argument is slightly different. It seems to me (on very quick scan) that Bird seems to argue not from QRPs, but from the source of hypotheses (theory or not, e.g.):0 replies 0 retweets 2 likes
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.