Delusional NY Times Op Ed tells us nothing about statistics but heaps about the pathologies of the bougie mind
Evidence suggests that the Cult of Vaccine has become a profound mental illness akin to schizophrenia or dissociative disorder
Berenson has already written about this. Ann Tomoko Rosen wrote a good piece about it too. But this NY Times Op Ed is so pathological that I wanted to spend some time examining its errors and the wider lessons that stem from its publication.
The title alone is a warning that this article is going to be a doozy!
That sort of framing is exactly how paid Pharma trolls on Twitter construct their tweets. “I’m a mom of three kids and deeply skeptical of authority but I desperately want the FDA to approve more injections for kids or I’m going to pull my hair out.” And then you click on their profile and notice that they do not have a profile photo, only have 10 followers, and every tweet reads like a drug commercial. Anytime they lead with this sort of demographic virtue signaling, proceed with caution.
The purported author of this piece, Aubrey Clayton, claims to be a “mathematical statistics researcher” with three children under four years old. I’m not sure what to make of his squishy job title. But I will take him at his word that he has three children. He does not mention whether these children have any chronic illnesses but let’s assume that they are healthy. For some strange reason, Mr. Clayton desperately wants to inject them with genetically modified mRNA:
As a parent of three children under 4, I was hit hard by last month’s announcement that the Food and Drug Administration was delaying its review of Pfizer-BioNTech’s Covid-19 vaccine for children under 5.
Like that of many caregivers guarding young children against the coronavirus, my winter has been full of rapid tests, mask reorders and outdoor play dates in borderline frostbite conditions. I’m able to manage this because I believe it’s temporary; we just need to hold out a little longer until our children can get vaccinated.
So Mr. Clayton is Very Afraid(TM) and he wants us to know that the only cure for his fright is to inject toxic, experimental, genetically modified mRNA into his kids.
Already it’s clear that Mr. Clayton does not understand statistics nor risk. And there are hints that he may have Stockholm Syndrome + Munchausen Syndrome by Proxy.
At this point I think it’s important to lay out the facts before Mr. Clayton gets drunk on unicorn sauce and starts trying to smash the furniture.
➡️ According to the Lancet, the infection fatality rate (IFR) from coronavirus in all children age seven and younger is 0.0023%. Nearly all fatalities in this age group had one or more underlying health conditions. With the emergence of the Omicron variant, the IFR is even lower.
➡️ Masking kids is not supported by the scientific evidence.
➡️ The Pfizer vaccine has already failed TWO clinical trials in this age group. Pfizer and the FDA acknowledge that this shot provides no protection for children.
➡️ There are already 8,817 reports of injuries from the Pfizer shot in kids 5 to 11 in the four months since this shot was given Emergency Use Authorization. This is the most dangerous vaccine in the history of the U.S. vaccine program.
So if you’re sane and a NY Times Opinion Page editor reading his pitch, you would reject this proposed Op Ed right away and give some serious thought to calling Child Protective Services to give them a heads up about this guy.
But we do not live in a sane world. The pathologies in the Op Ed apparently matched the biases of the NY Times so they went ahead and printed it.
After demonstrating that he knows absolutely nothing about this topic other than what he sees on the TV, Mr. Clayton asserts that he’s an expert and he’s here to help.
But because I study statistics, I also believe that if the data had been assessed in a more nuanced way, we might be putting vaccination appointments on the family calendar right now.
Oh dear. This is quickly becoming a dumpster fire.
As I explained above, Mr. Clayton has a problem because the data do not justify his fears. But Mr. Clayton has a solution — bend the data to fit his biases and destroy the entire field of statistics in order to save it!
Mr. Clayton goes on to construct an elaborate fantasy. In his Bizarro Upside Down Team Pharma World, he argues that the FDA is too strict with its insistence on statistically significant results. He explains that the the American Statistical Association is upset with statistical significance as well, and that the only solution is to discard frequentist statistics and evaluate these vaccines using Bayesian statistics.
It just so happens that this is a topic that I know a lot about. I spent three months during my Ph.D research studying the statistical methods used in evidence based medicine — and how the pharmaceutical industry has hijacked these methods to serve their profit interests. I’m not a statistician. But I use these tools enough to know that Mr. Clayton is completely off-base.
Like any bold lie, there is a tiny kernel of truth in Mr. Clayton’s rant. There was indeed a war within the field of statistics between the frequentists and the Bayesians — and the Bayesians won in a rout. But other than that, the key points in his narrative are the exact opposite of how he portrays them.
Contrary to his claims, the American Statistical Association is NOT upset with statistical significance because it is too stringent. Rather the American Statistical Association is urging people to move away from statistical significance because it is too lax. If a p value can tell you that 19 times out of 20 the result was not just due to chance — well, the possibility of being wrong up to 5% of the time is unacceptably high when it comes to medical products.
In the case of Covid-19 shots, that have been injected 554 million times into Americans in the past year, a 1 in 20 possibility that clinical trial results might have been wrong is potentially catastrophic. Remember, the 2008 global financial collapse happened because Wall Street firms were using Value At Risk models that were correct 99% of the time. But a 1% risk, with 253 trading days a year, means that the undesirable result will happen 2.53 times per year. The unacceptably high 1% risk is now called a Black Swan event.
Experts in the field argue that the standard for statistical significance should be 5 sigma (see Richard Horton, Editor-in-Chief of The Lancet, “What is medicine’s 5 Sigma”). Dr. Horton writes:
Tony Weidberg is a Professor of Particle Physics at Oxford. Following several high-profile errors, the particle physics community now invests great effort into intensive checking and re-checking of data prior to publication. By filtering results through independent working groups, physicists are encouraged to criticize. Good criticism is rewarded. The goal is a reliable result, and the incentives for scientists are aligned around this goal. Weidberg worried we set the bar for results in biomedicine far too low. In particle physics, significance is set at 5 sigma — a p value of 3 × 10^–7 or 1 in 3.5 million.
So the Editor-in-Chief of The Lancet wants a p-value of 1 in 3.5 million and this knucklehead writing in the NY Times thinks that a p-value of 1 in 20 is too stringent.
The article I just quoted is from 2015. Since then leaders in the field have pushed for six sigma — even more stringent. “A six sigma process is one in which 99.99966% of all opportunities to produce some feature of a part are statistically expected to be free of defects.”
Imagine a world where our biomedical products were that good.
Of course the FDA has lax standards in order to approve as many pharmaceutical products as possible, regardless of the consequences. If the FDA moved to a six sigma standard — as it should — all vaccines would fail the approval process. If the FDA moved to higher standards, millions of Americans would be spared a lifetime of chronic illness that results from iatrogenic injury.
But let’s return to Bayesianism for a moment because I feel compelled to rescue this important statistical approach from this numpty.
Frequentist statistics is binary. It’s a light switch. Something is either true or false (with a less than 5% chance that the result was just random — that’s statistical significance). But we all know that the real world is more complicated than that. And more importantly, information is not fixed, new information is always coming in.
In the 18th century, English statistician, philosopher, and Presbyterian minister Thomas Bayes came up with a theorem that enables one to steer as one goes. His method has come to be called Bayes’ Theorem. It’s conditional probability — the probability of an event occurring, given that another event has already occurred. Bayes moves statistics from a false sense of certainty to more realistic probabilities.
But then one can go one step further to create Bayesian decision trees — the probability of an event given a whole series of prior events. Get a bit of information, calculate the probability of each possible outcome, get a bit more information, add that into the model to update the precision of the estimate, repeat.
Bayes’ Theorem was used to find the missing Air France Flight 447. Statisticians get so jacked about Bayesianism that they write books like, The Theory That Would Not Die: How Bayes’ Rule Cracked the Enigma Code, Hunted Down Russian Submarines, and Emerged Triumphant from Two Centuries of Controversy.
So shifting to Bayesianism sounds pretty good right?
But Mr. Clayton doesn’t understand Bayesianism — at least not when it comes to vaccination decisions. Instead Mr. Clayton is engaged in a sort of statistical forum shopping — switching from one approach to another in hopes of getting the outcome that he wants. In switching to a probability model, Clayton hopes that the FDA might approve the Pfizer shot in young kids, with zero evidence of efficacy.
Here’s why that’s not going to work:
A frequentist approach to vaccines is to ask, ‘is it safe or not, does it cause adverse events or not.’ That’s what the FDA does now. It’s crude and overly simplistic. Given the complexity of human bodies and these biological products, it is a grave error for the FDA to use (and for doctors and parents to rely upon) such a primitive approach. Even so, most vaccines would fail the approval process if proper frequentist methods were used, as explained above.
A proper Bayesian approach to vaccines would be to ask: what’s the probability of an adverse event, given another family member who had an adverse event, the risks of each individual vaccine ingredient, the age of the child, the weight of the child, the sex of the child, the race of the child, and the number of vaccines given at one time. But I should add — even though this is the correct approach — this has never been done. My sense, having worked in this space for 7 years now, is that if one built the proper Bayesian decision tree for vaccines, the probability of harm would be enormous — approaching 100% if one modeled the entire U.S. vaccine schedule.
Mr. Clayton is aware of none of this. He is arguing, against all evidence and logic, that the FDA would approve the Pfizer vaccine in young kids — with zero evidence of efficacy — if it shifted to a Bayesian approach. He is completely wrong. But it is very difficult to argue with crazy people.
To recap: in the real world, the problem with statistical significance as it is currently used is that it is too lax, not too stringent. Experts in the field urge a move toward five sigma or six sigma as the threshold for statistical significance in connection with medical products. Bayes’ Theorem is great and should be used to evaluate vaccine safety. It does not matter which statistical approach ones uses, Covid-19 vaccines in kids under 5 would be a colossal mistake. If one uses a proper frequentist or Bayesian approach none of these vaccines would ever be approved and the U.S. would discontinue the vaccine schedule immediately.
Here’s the point that I want to make:
Statistics is a body of knowledge. It has a set of methods and best practices. It is not perfect and is always-evolving. But it has an internal logic that one can use to arbitrate disagreements within the field.
Mr. Clayton claims to be an expert in statistics.
But when Mr. Clayton tries to apply his beloved professional training to the topic of vaccines, something goes haywire. He sees the word vaccine and he behaves like a participant in a mind control experiment that has been given the code word that triggers psychosis. Suddenly up is down, day is night, dogs are cats, standards that are too lax are call too stringent, methods that would lead to the categorical rejection of this product are shaken up, spun around, and used to justify injecting experimental toxic substances into kids with no benefit. This is very strange.
How does this happen? What is it about vaccines that turns bougiecrats into psychopaths? What is it about vaccines that causes Mr. Clayton to abandon all of his professional training and instead torture these methods until they produce false claims? The topic of vaccines appears to cause a sort of permanent delusional hypnosis in bougiecrats that distorts their perceptions worse than LSD.
I have reluctantly reached the conclusion that the bourgeoisie is not just wrong about vaccines, but that their worship of this failed product represents a profound mental illness akin to schizophrenia or dissociative disorder. What is more, under the reality-distorting influence of this mental illness, bourgeois institutions like the NY Times are engaged in a fierce and determined campaign to completely discredit and humiliate themselves, so that no one ever trusts them again.
Now I’m wondering if the NY Times is just straight up trolling us? Dave Chapelle has this funny sketch about “Clayton Bigsby, the World’s Only Black White Supremacist.” And here the NY Times gives us “Aubrey Clayton, a Statistician Who Hates Statistics.” Was Clayton’s whole article just a prank — a fierce satire of The Cult of Vaccine? Alas, I wish the NY Times and Mr. Clayton were just pulling our leg with their version of the Sokal Affair updated for Covid craziness. But I fear that the NY Times and Mr. Clayton are being literal and actually believe his preposterous Pharma disinformation.
Many brilliant statisticians including Mathew Crawford and Jessica Rose (subscribe to them, they’re amazing!) read my Substack and will doubtless be able to improve upon what I’ve written here. But in the interests of dialogue I’m going to press publish and we can continue the conversation in the comments section.
Blessings to the warriors. 🙌
Prayers for Canadian political prisoner Tamara Lich who is still being held without bail for the crime of “mischief.” 🙏
Undermine fascism always and everywhere. ✊
In the comments, please let me know your thoughts.