Something that I keep seeing pop up is the idea that meta-analysis somehow eliminates issues with the underlying research This is just confusingly incorrect
-
-
Some people think meta-analysis is impressive because it involves fancy statistical software, but it's entirely possible to implement a Dersimonian-Laird inverse-variance model in Excel with a stats textbook and a few hours of time
Show this threadThanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Yup. I was going to say GIGO at the first tweet. No analysis can fix bad data.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
It’s worse than GIGO. Many meta-analyses will combine well done large trials with garbage, basically ruining the well done trials.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Taking random studies at face value and applying a meta-analysis model is indeed GIGO. But that's not how a _good_ meta-analysis study is done.
-
If there is an unresolvable bias, error, or fraud - you eliminate the study. This is what quality "reviews" do (like Cochrane's).
- Show replies
New conversation -
-
-
One of the issues I have with Cochrane in particular is that they throw out a LOT of studies, and what remains mushifies (a word I just made up) the issue instead of bringing clarity. Why publish a analysis at all if the conclusion is "all the studies are crap"?
-
Because that's an important finding. If the studies are insufficient to determine a conclusion, we shouldn't be promoting a treatment based on them!
End of conversation
New conversation -
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.
