Frustrated watching people tout an RCT where the paper only reports 2 between-arm comps, both consistent with null effects (& neither appear in the abstract), and a gazillion within-arm "results" that are then used to make it seem like the intervention was amazingly effective.
-
Show this thread
-
Why even run the RCT? Why can't scientists see through this? Are people just nodding their heads and repeating after the teacher that control groups are important, but not actually understanding why?
8 replies 1 retweet 17 likesShow this thread
Replying to @statsepi
Most of the time when I see this there are obvious competing interests behind the nonsense. One memorable case recently where Nestle funded a study into coffee - 40-odd between-arm comparisons, 2 significant, 1 in the wrong direction Conclusion = coffee effective!
12:33 AM - 18 Feb 2020
0 replies
0 retweets
5 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.