My least favorite version of this: i) calculate difference from baseline in control group ii) calculate difference from baseline in experimental group iii) if the confidence intervals of i) and ii) don't overlap, conclude there is a significant effect of treatmenthttps://twitter.com/statsepi/status/1410516562444959747 …
-
-
Replying to @MaartenvSmeden
Yeah, but what if you could get that published in the NEJM? Because you can!
2 replies 0 retweets 10 likes -
Replying to @statsepi @MaartenvSmeden
Ironically, the only trials in NEJM where you rarely see this sort of thing are the ones funded by pharma because the ghost writers check with their statisticians before submission
1 reply 0 retweets 4 likes -
It’s not ironic. On the one hand you have checks done by salaried professionals on the other hand it’s unpaid “volunteer” “peers”.
1 reply 0 retweets 6 likes
You're right, I suppose that was more the colloquial use of irony than the correct one 
2:56 PM - 1 Jul 2021
0 replies
0 retweets
0 likes
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.