The Chloroquine Wars Part CXVI

“At the moment, he is suffering from delusions of adequacy.” -Walter Kerr

Source: The Mentally Ill Hero: How the Tick and Dirk Gently give Unbalanced “Sidekicks” Center Stage

Sometimes it’s not quite as funny as an episode of The Tick.

Dr. Lynn Fynn (Fan Account) @fynn_fanAwww look at the witch hunters digging up studies from 5+ years ago that went through vigorous peer review for the sole purpose of targeting those that make them look bad. He most certainly did NOT fabricate data. This sort of accusation is defamatory. This won’t end here. 😉 https://t.co/JHoR9aKclaKyle Sheldrick @K_SheldrickThis study by a “Paul E Marik” and others claiming a reduction in Sepsis mortality with Vitamin C at “Sentara Norfolk General Hospital” contains obviously fabricated data. I will write to the Author, Hospital and Journal tomorrow requesting retraction. https://t.co/0sfUqkSD0VMarch 24th 202224 Retweets107 Likes

Recall that Kyle Sheldrick is part of the Superfriends team, tickling each other en route to finding flaws in studies of early treatment efficacy despite the successful treatment of hundreds of thousands of patients by doctors such as Brian Tyson, George Fareed, Ben Marble, Didier Raoult, Pierre Kory, Heather Gessling, and so on, with a collective survival rate in the ballpark of 99.97%.

Rounding the Earth Newsletter

The Meta-Analytical Fixers, Part II: Public Servants or Middling Saboteurs?

I don’t have time for this level of garbage, so I won’t spend much on it, but something needs to be said. The propagandists vastly outnumber the people of good faith in The Chloroquine Wars, if that is now my general term for this medical authoritarian battle…Read more6 months ago · 58 likes · 29 comments · Mathew Crawford

Such numbers from early treatment doctors go far beyond the power-need of RCTs—out beyond the realm where the published literature confirms, “This RCT/OCT distinction clearly doesn’t matter anymore.”

Rounding the Earth Newsletter

A Critique of RCTs: Historical Failure to Strike Gold

“History is the best teacher, who has the worst students.” -Indira Gandhi In our last article, we demonstrated RCTs are neither the highest form of scientific experimentation, nor are guaranteed to achieve their goal of proving superior testing. In this article, we examine the empirical history of RCTs, and compare the data from RCTs with “lesser” forms …Read morea year ago · 19 likes · 5 comments · Mathew Crawford

So, what’s all the fuss about this time, Sheldrick?

http://kylesheldrick.blogspot.com/2022/03/evidence-of-fabricated-data-in-vitamin.html

Tonight on twitter a paper allegedly describing a 2017 study by a “Paul Marik” and team at Sentara Norfolk General Hospital describing a large survival benefit from Vitamin C was brought to my attention as a medical research finding that was not replicated in further studies and later reversed. The user stated that to their knowledge no evidence of fraud in the conduct of this study had been identified. The study is found at https://doi.org/10.1016/j.chest.2016.11.036

Unfortunately within about 5 minutes of reading the study it became overwhelmingly clear that it is indeed research fraud and the data is fabricated.

While usually I would use cautious language of “unusual” or “unexpected” patterns in the data and describe “irregularities” and “concern”; no such caution is warranted in this case. This is frankly audacious fraud. I have not requested access to the raw data or contacted the authors for explanation as the case is audacious no other explanation is possible.

Allow me to explain.

You sure, bruh?

This study allegedly describes a before and after study, examining the effect of a new treatment regime based on vitamin c on mortality in sepsis, claiming a roughly ten fold reduction in death. Each cohort had exactly 47 patients and the patients were not matched. We know this not just because matching was not mentioned but because the authors specify that these were two cohorts of “consecutive” patients, precluding patient matching by definition.

Oh dear, we have a “by definition” that isn’t…based on definition, but rather on Sheldrick’s lack of knowledge of statistical methods or imagination (either would suffice).

Sheldrick then proceeds to apply a statistical test (Fisher) with respect to the wrong distribution, based on his faulty logic.

I take issue with the way p-values are even computed here. A (5,5) happens around a quarter of the time, so the 1 in this case is an artifact of a computational process that is not actually centered around 0.5, and the skew is not actually small. Though clearly Sheldrick is not aware of the difference between the actual computations and what he read out of some textbook or a page off the internet, lacking context. But that’s beside the main point…

There are infinitely many statistical rubrics that data can be churned through, and a combinatorially explosive array of distributions against which the statistical tests can be performed. Most of them aren’t particularly meaningful. But the goal is to find the one(s) that have the most meaningful relationship with reality in our judgment.

Sheldrick assumes he has the correct one—I suspect because he thinks that it’s the only one. Then, when he gets “unlikely results”, he doesn’t question his choice of distributions. Instead, he declares Marik to be a fraud.

Allow me to explain…

Understand that the Marik paper is behind a paywall, so I haven’t actually read it. Technically, I could be about to incorrectly describe the way the study might have been conducted. But the point is that Sheldrick is absolutely incorrect in his assumption that there is no randomization at play that would be expected to result in fairly well balanced trial arms.

Mathew’s Almost Random Algorithm for Consecutive Patients

For simplicity, consider each attribute for which Sheldrick computed a p-value to have a 0 or a 1. For instance (male 1, not male 0; comorbidity 1, no comorbidity 0; etc.).

• Step 1: Start by treating the first patient.
• Step 2: For each subsequent patient, put them into the treatment or control group according to which one results in the lower sum of differences (or difference between sums is pretty good, too) between the arms (summed binary values as above). If those are equal, chose according to most confounding variable (most associated with mortality) to rebalance the arms, and continue down the line of selection. If the arms were perfectly balanced, treat as Step 1.
• Step 3: Once one of the arms is filled, the last 1-to-several patients go in the other arm.

I’m not going to bother computing the p-values. But I giggle at the thought of whether Sheldrick would know how. Hey there, Sheldrick, ole buddy, do you know what this distribution is going to look like, or how to compute a p-value, now?

My algorithm is designed to induce mean-reversion of stats. I could easily improve the algorithm, but you see my point? Sequential patient selection does not necessarily result in the distribution that he thinks it does, so his p-values don’t mean what he thinks they mean. His claim of fraud could be correct, I suppose (I doubt it, but perhaps the world has conspired against me in fooling me to trust Marik or think that Vitamin C could be helpful…to a mammal that doesn’t produce its own internally). But he isn’t correct based on anything that he’s said so far. He really just looks like a Pfucking idiot, pardon my language.

If Marik sues Sheldrick now, there’s really only one thing left for me to do.