Covid Is The Boogerman of Maladies: Now It Causes Cognitive Confusion Claim Researchers

So these researchers said the worse infection of covid you had the more you now act like our dear President:

In a multiple regression analysis, participants who had recovered from Covid-19 in whom symptoms had resolved in less than 4 weeks or at least 12 weeks had similar small deficits in global cognition as compared with those in the no–Covid-19 group, who had not been infected with SARS-CoV-2 or had unconfirmed infection…; larger deficits as compared with the no–Covid-19 group were seen in participants with unresolved persistent symptoms… 

The peer-reviewed paper is “Cognition and Memory after Covid-19 in a Large Community Sample” in NEJM by Hampshire and others.

The first clue something has gone wrong comes in the words that cause, or should cause, shudders in any sane reader: multiple regression analysis. The initial reaction should aways be, “Uh oh. What have they done now.” You can get away with the statistical equivalent of murder with regression. You and I over the years have seen what amounts to conventions of serial killers on a spree using regression.

Is that true here?

They got data from the UK’s NHS and asked a bunch of people in that system to do some quizzes. Then they busted up the data like this:

We categorized participants into six groups according to the duration of SARS-CoV-2 infection.⁷ Categories 2 through 6 required positive results on a PCR test, lateral flow immunoassay, or participant-reported test. Category 1 was defined as “no Covid-19” (i.e., the participant had not had SARS-CoV-2 infection or had an unconfirmed SARS-CoV-2 infection), category 2 as asymptomatic SARS-CoV-2 infection, category 3 as resolved short Covid-19 lasting less than 4 weeks, category 4 as resolved short Covid-19 lasting at least 4 weeks but less than 12 weeks, category 5 as Covid-19 symptoms that resolved at least 12 weeks after infection onset, and category 6 as Covid-19 symptoms that persisted at least 12 weeks after infection onset and had not resolved at the time of the cognitive assessment.

Maybe you don’t remember, but in the midst of the panic there were two stories that didn’t get a lot of coverage. The first (linked here) was Experts lamenting how some people were ignoring their raging covid infections because they were so minor that many thought it was a mild allergy. Experts wished they could at least act like they were panicked.

The second (linked here) was from the CDC doing its job (it happens) and estimating a huge chunk of the population had got covid by January 2022 but never knew it. You may also remember the hersteria (there is no misspelling) over “asymptomatic transmission.”

Point is, it’s very likely almost everybody has had covid, but not everybody was tested for it or suffered from it. Particularly the young skipped incessant testing—and skipped panicking. Also, the infections the young, and old but healthy, got were also much milder on average, even unnoticed.

This means our researchers’ first two categories are likely the same kinds of people, and not separate. A minor error.

The second error comes in answering these questions: Who does better at these cognitive quizzes, the old or young? Or the easily panicked or sober? The hersterical or the calm? The people who took their symptoms stoically and forgot about them or those who freaked out, cherished their disease, got a shot each time they say a propaganda booster, and now blame every new ache and pain on “long covid”?

The third mistake, which is similar to the second, and one that is unfixable in the current set up, is that we have no idea what peoples’ scores were before the panic. The authors only present one snapshot of data after the fact. That means we cannot—where I use cannot to mean can not—infer the direction of causality from the data alone.

It may be that worse covid caused worse thinking. But permanently? How? Does flu do that? Colds? Another explanation is in the scenarios I painted: worse thinking caused the worse (claimed or real) covid symptoms. That is, less cognitively able people either had worse covid, or complained they did. Plus, we don’t know anything about the dead, which is the worst covid of all. In any case, the worse symptoms, including death, were much, much more likely suffered in the old. The very group that would score worse on these tests.

“But Briggs, they said they controlled for age in their hugeous multiple regression model.”

I have said it too many times to remember, but “control” in a statistical model has nothing to do with how you control for, say, salt in a recipe. You put more or less salt to adjust to your taste. “Control” in a regression does not work like this. It causes changes in the parameters, adjusted for all other parameters in the model. It is a parameter-based maneuver with only distant ties to Reality. And there were many, many, oh many, parameters. Here’s a portion of them (from the Supplementary material):

All this is before the various other statistical tricks played, like something called propensity score matching. This is a self-referential system to group data, resulting in models of models that doesn’t account for all uncertainty. Worse, the differences “discovered” are small anyway, and only seem important because of the large sample size, which guarantees wee Ps and narrow confidence intervals—even if nothing is causally happening. They see this themselves, but don’t see it, when they say “Although previous, often underpowered, studies have offered contradictory evidence for associations between mental health and cognitive deficits after Covid-19,^5,37,38 our study was powered to detect small associations with high confidence.” Even if so, it does not get the direction of cause.

Which again they see but don’t see, when they say, “This study has certain limitations, including reliance on subjective reporting to identify persons with persistent symptoms. The relationship of our results to the literature about long Covid is complicated owing to a lack of established, defining criteria for post–Covid-19 syndromes. “

There is no word whether The Leader of the Free World™ took one of these tests.

Subscribe or donate to support this site and its wholly independent host using credit card click here. Or use the paid subscription at Substack. Cash App: $WilliamMBriggs. For Zelle, use my email: matt@wmbriggs.com, and please include yours so I know whom to thank.