Just a quick reminder that if you have a randomized trial comparing intervention to no intervention & there is non-adherence, your intention-to-treat estimate will be closer to the null than the true intervention effect. Remember this when reading trial results today.
-
-
Replying to @EpiEllie
Per Damkier Retweeted Per Damkier
There appears to be quite a quantitative gap between "exactly as described" and "no, not at all". Which is apparently fully covered by the category "predominantly as described"...https://twitter.com/Per_Damkier/status/1329153425741926400?s=20 …
Per Damkier added,
1 reply 0 retweets 7 likes -
Replying to @Per_Damkier
Adjustment for non-adherence is made a million times harder by not collecting good adherence data!!2 replies 1 retweet 20 likes -
YIKES.
1 reply 0 retweets 2 likes
Replying to @NoahHaber @EpiEllie and
I second this YIKES. That is a ~terrible~ way to collect adherence data!
1:51 PM - 18 Nov 2020
0 replies
0 retweets
1 like
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.