Hey #epitwitter, a question. At what point does the heterogeneity across epidemiological studies make the meta-analysis pointless (or at least too vague to be useful)?
Definitely, but the suggestion is that this is impossible if we can't meta-analyse things at all. I'm not sure I entirely agree with that
-
-
Theoretically it seems possible. If someone designed a study, with explicit instructions on how to collect the data, and if multiple researchers used those instructions, then it seems that I^2 would be a good measure for the heterogeneity between the data from each researcher.
-
But It is possible that there is an over reliance on I^2 in some meta analyses. A general overview from what I recall from in meta analyses that I have read in Epi: multiple studies were collected from a lit review, with a particular response and covariates of interest...
- Show replies
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.