An example: there was underlying selection bias that led to a 'sicker' control group (however we define sicker). Given the small sample size, the logistic model cannot adequately control for this issue, and so the results are hard to interpret
-
-
-
Replying to @saarwilf @Rootclaim
It's pretty complex, but basically once you're into the single digits it's hard to draw much meaning from logistic models i.e.https://bmcmedresmethodol.biomedcentral.com/articles/10.1186/s12874-016-0267-3#Sec12 …
1 reply 0 retweets 0 likes -
They discuss overestimation of covariate-outcome relation. In our case where the covariates are the risk factors, it means the effect of VitD is actually larger. In any case, even if you assume only people with hypertension go to ICU, the result is significant (see our analysis).
1 reply 0 retweets 0 likes -
Replying to @Rootclaim @saarwilf
I mean, that's not true and it mostly misses the point so...I disagree. It really comes back to the fact that a tiny pilot study doesn't form a strong basis for decision-making
1 reply 0 retweets 0 likes -
Replying to @GidMK @Rootclaim
You need to think risk/reward. What is the probability that the study is completely wrong, what is the risk of treatment, and weigh those to make a decision with positive expected impact on patient health.
1 reply 0 retweets 1 like -
Replying to @saarwilf @Rootclaim
I always find that attitude striking. HCQ was recommended on the same basis, and with arguably much better evidence, and now we know it doesn't work at all and we've wasted vast sums and potentially harmed millions. It is not such an easy either/or, I think
1 reply 0 retweets 0 likes -
Replying to @GidMK @Rootclaim
HCQ was exactly how not to do science. No RCT, no history of effectiveness against respiratory viruses, no multiple correlation studies, no causal models, no clear mechanism of action. It's like rejecting vaccines, because doctors once used leeches and it failed.
1 reply 0 retweets 0 likes -
Replying to @saarwilf @Rootclaim
The HCQ proponents would argue precisely the opposite. And vitamin D has a long, long history of being touted as a cure for every disease under the sun and failing to show a benefit in rigorous RCTs
2 replies 0 retweets 0 likes -
Replying to @GidMK @Rootclaim
It doesn't matter who says what, and what claims were wrong. Each claim should be evaluated independently in light of the evidence, then assess the risks and maximize expected outcome. Good summary of current evidence: https://github.com/GShotwell/vitamin_d_covid …
1 reply 0 retweets 0 likes
That website just cites the exact same evidence we've been discussing, but in a different form. And I agree - that is precisely my point
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.