Quote:
Originally Posted by skyking
So 47 is a "small study" but 181 is a statistically valid study. I knew my statistics professor was misinformed. Or is it if the findings agree with your position which make it relevant?
|
I don't actually understand the point you are making. Of course with a larger sample size it is easier to detect statistically significant differences. It is also easier to detect that sample groups do not differ significantly. Yes, 181 is greater than 47. Thus a study with 181 data points if looking at the same conditions, for the same outcomes, with the same variables... Will be a stronger study.
I do not have a position on whether or not HCQ works. I have made that clear over and over and over. I do have a position on whether it has been shown to beneficial in well conducted studies. It has not. Will it be shown to be beneficial in studies now ongoing. I don't know. I believe in the scientific method, not making judgement about efficacy by gut feeling.
So this particular retrospective chart review had enough numbers that its findings should be considered a possible refutation of extreme benefit of HCQ for Rx of Covid in the patient type studied. I did point out in my initial post that this is not peer reviewed nor published yet, as I have in I believe every study I have mentioned from the medrxiv.
I will continue to read the literature daily. I will continue to post updates to TOTV on both positive and negative outcomes. I will continue to point out what I believe are cautions to be considered in study design, patient selection, randomization, etc.
Some proponents of HCQ have claimed, as linked on TOTV, that they see nearly 100% recoveries with the drug given alone . Sometimes they claim it only works if given with azithromycin. Those two claims cannot both be true. Others claim that it doesn't work unless you give it with zinc. So that's three separate protocols each claiming a high rate of benefit, but 2 of the 3 saying the other two would fail. The "need zinc" guy says HCQ fails if taken alone or taken only with Zith. The "you need zith" guy says if you only add zinc to HCQ you have missed the needed booster.
This thread is about treating or not treating moderately ill hospitalized Covid patients with HCQ and seeing if it helped.
Quote:
Interpretation
These results do not support the use of HCQ in patients hospitalised for documented SARS CoV-2-positive hypoxic pneumonia.
|
If you want to discuss statistics I refer you back to the actual paper
HERE in which the authors inform you of the statistical tools used in great detail.
"Statistical analysis
An inverse probability of treatment weighting (IPTW) approach was used to “emulate” randomisation and balance the differences in baseline variables between treatment groups.10,11 A non-parsimonious multivariable logistic regression model was constructed to estimate each patient’s probability of receiving HCQ given their baseline covariates (i.e., the propensity score). Variables of the propensity score (PS) model were planned and prespecified before outcome analyses and included …." and it goes on for nearly an entire page.
The results section lists both relative risk [RR] AKA odds ratio and the confidence interval [CI] for each outcome measured. Please look at those statistics and let me know if the sample size in this study was large enough to produce useful numbers.
My statistics professor did a good job too. I don't think mine was misinformed.