"Patients with underlying conditions were 12 times as likely to die of covid-19 as otherwise healthy people, CDC finds."

A WaPo headline, quoted along with substantial text from the article by my son John at Facebook, where I expressed surprise that the factor was so low and asked:

Did they count obesity as a "condition" when they did that calculation?

Then:

I looked at the CDC report, and I see it only counted "severe obesity (body mass index ≥40 kg/m2)" as a condition. I'm a 5'5" woman, and I would need to weigh more than 240 pounds — more than 100 pounds over normal weight — to enter that BMI range.

Obesity begins at a 30 BMI, which would be 180 pounds for my height. That's 60 pounds less than the weight the CDC counted as a "condition" when it did its calculation. It wouldn't be 12 times as likely but what? — 100 times? — if they'd included the merely obese. And what if they'd counted the overweight but not obese? That would go all the way down to 150 for my height. It would be useful to know, because we have some power over our own weight!

ADDED: My son questions my observation. The factor should be lower if they included less severe conditions. I agree with him. I'm thinking in terms of being less likely to die. When you're trying to figure out how dangerous the illness is to you, you consider how likely it is for a person in your condition to die if they get the disease. Perhaps it's the case that 99.9% of those who died of the disease were obese. Of course, that's not the same as saying if you get the disease and you're obese, you have a 99.9% chance of dying. But if the overall percentage of those who get the disease and die is 0.1%, then I'd like to know what's the percentage for those who get the disease but are not obese? Is it 0.01%? That would be extremely useful information! For one thing, it would give people something to do to protect themselves: lose weight. But also, it would show us who should continue the more extreme form of social distancing and who should feel free to get out and about.

"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.

"Density alone doesn’t seem to account for the scale of the differential between New York’s fatality rates and those of other cities."

"New York has twice the density of London but three times the deaths, and the differential is even higher [comparing NYC to] cities such as San Francisco and Los Angeles. Deaths have occurred disproportionately in poorer areas, where the incidence of long untreated morbidities such as heart disease and diabetes have contributed significantly. But the same is true in all other cities. The high dependence on mass transit also seems to be a factor. In other major cities, car commutes are much more common. As Joel Kotkin, a scholar of cities at Chapman University in California, says, it may be the lethal convergence of all three factors. 'If you put together density, levels of poverty and reliance on a mass-transit system, you have a hat trick,' he told me.… But even that may not explain the extent of New York’s unique catastrophe. Around the world, the highest death rates have occurred where hospital systems were overwhelmed in the early stages of the crisis. This is especially true in northern Italy. Anecdotally, at least, it seems that the same happened in New York: Large numbers of sick people never got to hospitals, arrived too late or, in the impossible circumstances that medical personnel were confronted with, were given ineffective treatment.… It will be a while before we get a proper understanding of what went so tragically wrong...."

From "The Covid-19 Catastrophe Unfolding in New York Is Unique" (Wall Street Journal), quoted at my son John's Facebook page.

John writes:

I'm not sure this is a logical argument:

"Density alone doesn’t seem to account for the scale of the differential between New York’s fatality rates and those of other cities. New York has twice the density of London but three times the deaths, and the differential is even higher for cities such as San Francisco and Los Angeles."

Doesn't that assume there's a linear relationship between density and infection rates, and isn't that not necessarily the case?

My question is about the comparison of New York to northern Italy, where hospitals were overrun. Were NY hospitals overrun? I thought they weren't.  I think the 3 factors named — density, reliance on mass-transit, and the bad health conditions represented by the term "poverty" — are enough to explain what happened. These things are interactive. Shouldn't we talk about Bayes theorem?