In this case, the risk of bias was quite closely linked to a) sampling methodology and b) reporting Studies that used a biased sample and/or didn't report methodology got lower scores
-
-
Show this thread
-
The risk of bias came from this scoring methodology https://www.clinicalkey.com.au/#!/content/playContent/1-s2.0-S0895435612000790?scrollTo=%23appsec1 …
Show this thread -
Another interesting point - it's about more than age! Overall IFR doesn't track well at all with median age of country. Might be down to who has been infected where, but imo it's more complicated than just demographicspic.twitter.com/bbgmBNiMsT
Show this thread
End of conversation
New conversation -
-
-
We consider how one could incorporate these varying degrees of biases in a Bayesian model: https://arxiv.org/abs/2005.08459 main conclusion: mildly informative priors could greatly reduce the uncertainty around the IFR.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
is there a link to the full study?
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Please can you share the link to the study.
- 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.