https://www.washingtonpost.com...4KOZCZPCB245HD7SIKMA

“A new study from Stanford University estimates that 18 of Trump’s recent large-scale campaign rallies ultimately resulted in 30,000 confirmed cases of the coronavirus and probably led to more than 700 deaths among attendees and others infected by them.

The study, released Friday by Stanford economics professor B. Douglas Bernheim and three doctoral students, examined rallies staged by Trump between June 20 and Sept. 30 and looked at the trajectory of cases in the counties in which they were held.”

The paper:

https://sebotero.github.io/pap...llies_10_30_2000.pdf

— — — —
We investigate the effects of large group meetings on the spread of COVID-19 by studying the impact of eighteen Trump campaign rallies. To capture the effects of subsequent contagion within the pertinent communities, our analysis encompasses up to ten post-rally weeks for each event. Our method is based on a collection of regression models, one for each event, that capture the relationships between post-event outcomes and pre-event characteristics, including demographics and the trajectory of COVID-19 cases, in similar counties. We explore a total of 24 procedures for identifying sets of matched counties. For the vast majority of these variants, our estimate of the average treatment effect across the eighteen events implies that they increased subsequent confirmed cases of COVID-19 by more than 250 per 100,000 residents. Extrapolating this figure to the entire sample, we conclude that these eighteen rallies ultimately resulted in more than 30,000 incremental confirmed cases of COVID-19. Applying county- specific post-event death rates, we conclude that the rallies likely led to more than 700 deaths (not necessarily among attendees).
— — — —

Of course, you might ask where are this type of studies for protests, religious gatherings, weddings, funerals, private parties, etc. Please ask loudly on all your social media channels ... maybe some researchers will pick it up.

This is a really tough measurement problem. Their county matching method seems like a perfectly sensible way to estimate the average effect, and the number of events seems large enough to have some confidence in the sign and significance if not the exact magnitude. I guess it helps that their results are reinforcing what one might expect rather than coming to some startlingly counterintuitive conclusion.

True, especially the last part. But if there were negligible impact from Trump's rallies, we wouldn't expect to see their results consistently. I'm intrigued by their quasi-placebo "control" group. I'll have to read it in more detail after my coffee has had a chance to kick in.

How sad.

But he doesn't care.

A H

quote:

Originally posted by LL:
How sad.

But he doesn't care.

A H

Naw. He is proud of it. His supporters are willing to die for him.

And so they do.