If a systematic review finds only small, poorly-done studies on a topic but they have mostly null results should it conclude #EpiTwitter
-
Show this thread
-
I think this is a really interesting question. On the one hand, if there are no good studies then we may not have answered the question. On the other, if we ignore pilot/small studies, what's the point of doing them in the first place?
2 replies 0 retweets 10 likesShow this thread -
And if we always call for more research, where does that end? Where is the cutoff between not an answer and an answer?
6 replies 0 retweets 10 likesShow this thread -
Replying to @GidMK
You need an "it depends" button!! I once saw a SR looking for associations between yoghurt and a health outcome (prospective cohort studies), concluded "More research needed" with >100,000 participants and a p-value of 0.14. At that level I think you can say "no association"
1 reply 0 retweets 1 like
Nah I'm not talking about SRs with large cohorts, I'm talking about n=200 from 9 studies most of which were at high risk of bias. What then? Do we call for more research or consider the question no longer worth pursuing?
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.