"The decision to buy a handgun for the first time is typically motivated by self-protection. But..."

"... it also raises the purchasers’ risk of deliberately shooting themselves by ninefold on average, with the danger most acute in the weeks after purchase, scientists reported on Wednesday. The risk remains elevated for years, they said," the NYT reports.

Thanks, scientists, but did you exclude the people who bought guns because they'd already formed an intention to shoot themselves? Or maybe it's just the NYT that wrote it that way, making it sound as though there are a lot of people who buy a handgun for self-defense and then somehow — once they've got that handgun — embark for the first time into suicidal ideation.

Of course, it's easy to see that people who have a gun are more likely to shoot themselves than people who don't have a gun, but they're talking about first-time handgun owners. So the comparison is first-time handgun owners and longterm handgun owners? NO!

The study tracked nearly 700,000 first-time handgun buyers, year by year, and compared them with similar non-owners, breaking out risk by gender. Men who bought a gun for the first time were eight times as likely to kill themselves by gunshot in the subsequent 12 years than non-owners; women were 35 times as likely to do so.

Well, the non-owners number would be extremely small, so 8 times that and even 35 times doesn't sound so big.

Toward the end of the article, there's a reference to "so-called reverse causation." That's the situation that I mentioned, above, that the handgun was bought for the purpose of suicide, but the researchers had no way to tell the difference between these people and those who bought the handgun for self-protection (and the protection of others).

I got the feeling the article was written to inspire readers not to arm themselves lest the gun would change them into a person who'd commit suicide. This is the message that if you don't want to die, don't arm yourself because you'll be arming your most-likely murderer: YOU!

Testing... your intelligence.

Not providing context on the increase in testing is such a basic error, and has been so widespread, that it's revealing about the media's goals. It's more interested in telling plausibly-true stories ("narratives") that sound smart to its audience than in accuracy/truth per se. https://t.co/abYbgkVFbj

— Nate Silver (@NateSilver538) May 7, 2020

"It’s a Bayesian thing. Part of Bayesian reasoning is to think like a Bayesian; another part is to assess other people’s conclusions as if they are Bayesians..."

"... and use this to deduce their priors. I’m not saying that other researchers are Bayesian—indeed I’m not always so Bayesian myself—rather, I’m arguing that looking at inferences from this implicit Bayesian perspective can be helpful, in the same way that economists can look at people’s decisions and deduce their implicit utilities. It’s a Neumann thing: again, you won’t learn people’s 'true priors' any more than you’ll learn their 'true utilities'—or, for that matter, any more than a test will reveal students’ 'true abilities'—but it’s a baseline."

From "Reverse-engineering priors in coronavirus discourse" by Andrew (at Statistical Modeling, Causal Inference, and Social Science,) via "What’s the Deal With Bayesian Statistics?" by Kevin Drum (at Mother Jones).

Both of these posts went up yesterday, that is, 2 days after I said, "Shouldn't we talk about Bayes theorem?" I'm not saying I caused that. I'm just saying maybe you should use Bayesian reasoning to figure out if I did. I will stand back and say, this is not my field. I'm only here to encourage it.