It's also worth noting that in the context of this meta-analytic model the p-value is entirely the result of the cherry-picking of "positive" values, so the chance of having a low p-value is 100% regardless of whether ivm works or not
-
-
Replying to @GidMK @K_Sheldrick
No, there was no cherry-picking. There was an extremely forgiving set of inclusion-exclusion criteria that let in some positive and negative results, but left out almost nothing.
2 replies 1 retweet 39 likes -
If you make such a claim, it's on you to identify the misplace study that was miscategorized according to the inclusion-exclusion criteria, because that's what cherry-picking means.
1 reply 0 retweets 6 likes -
Replying to @EduEngineer @GidMK
OK, are we doing this? Let's do this. Let's go through the first set. The prophylaxis studies. Viral positivity is the least important outcome so presumably the five here should not report any symptom, hospitalisation or mortality outcomes, will there be an error in these 5?pic.twitter.com/0TxoZ7hS7H
3 replies 5 retweets 19 likes -
I reckon we can review these 5 in 5 minutes, let's see.
1 reply 0 retweets 5 likes -
The very first study is by Prof Babalola from Lagos. It reports change in cough and dyspnea, by the authors' claimed rules this should have been extracted instead. In both cases the control did better. This error favoured ivermectin.pic.twitter.com/nKiXWm77iO
1 reply 0 retweets 10 likes -
Replying to @K_Sheldrick @GidMK
Okay, I think we disagree on what the criteria says.
2 replies 0 retweets 1 like -
I believe that what the author intends is that death > hospitalization > etc. It sounds like you want to throw symptom vs. symptom into that classification? If so, that's an argument for computing a p-value by a different definition of the criteria, not the the author...
2 replies 0 retweets 3 likes -
Replying to @EduEngineer @K_Sheldrick
The author says "severity". Obviously, viral positivity is less severe by any clinical definition than symptoms
1 reply 0 retweets 3 likes -
Replying to @GidMK @EduEngineer
They specifically say clinical outcome more important than PCR status.
1 reply 0 retweets 4 likes
You're right! So even by their own awful methodology, this is a terrible contradiction. Like I said, pseudoscience
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.