severe testing of hypotheses with or without pre reg can actually achieve a lot of what we want. But ppl won't do it
-
-
severity in the Mayo sense
1 reply 0 retweets 0 likes -
-
Replying to @o_guest @annemscheel
so it's kinda like Poppers use: test with a highly probability of detecting genuine effects but not non genuine
2 replies 0 retweets 1 like -
Replying to @ed_berry @annemscheel
link me! Sounds like some phil of sci I'd be interested in reading about - I'm not a Popperian though.
1 reply 0 retweets 0 likes -
-
Replying to @ed_berry @annemscheel
food is for the week
also thanks - I await with eagerness.2 replies 0 retweets 0 likes -
Replying to @o_guest @annemscheel
well the pain book is 'Error and the Growth of Experimental Knowledge', though there's a new one coming out >
2 replies 0 retweets 1 like -
then there's the blog over at https://errorstatistics.com/ . And this paper is a very nice summary http://www.phil.vt.edu/dmayo/personal_website/Error_Statistics_2011.pdf …
2 replies 0 retweets 1 like -
the discussion about the pickle people get into thinking pre-prediction is necessary is in the main book Chp 8 I think
1 reply 0 retweets 1 like
Obviously I have not read it but I'm @annemscheel will appreciate that chapter.
-
-
Replying to @o_guest @annemscheel
there's probably a blog on it/pre reg for something a bit shorter :)
0 replies 0 retweets 1 likeThanks. 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.
