Andrew Gelman on Bayesian analysis is the right framewor…

Andrew Gelman

Statistician and political scientist, Professor at Columbia University

It's hard to compute Bayesian probabilities for this problem, not so much because of the priors but because of the likelihood, which is the probability of the data given the model. One problem is the selection of what is considered to be data, the other problem is that the model ('lab leak' or 'wet-market leak' or whatever) is not clearly specified–in statistics jargon, these are 'composite hypotheses.'

AI Verified (Aug 1, 2025)

Source:

Statistical Modeling, Causal Inference, and Social Science blog

3mo ago

Policy proposals and claims

Bayesian analysis is the right framework for settling the COVID-19 origins question

votes Against

Statement relation verification history AI Verified Report this

AI Verified Yes. The quote is directly about whether Bayesian analysis can be used to resolve the COVID-19 origins question, and the source context immediately frames that difficulty as a reason the author is not convinced Bayesian inference is the right tool for this problem, making a determinate stance on the complete statement substantially more likely. ([statmodeling.stat.columbia.edu](https://statmodeling.stat.columbia.edu/2025/08/01/different-estimates-of-covid-origins-probabilities/)) · YouCongress gpt-5.4-2026-03-05 · 3mo ago

Vote inference verification history Latest opinion AI Verified Report this

AI Verified He gives methodological objections—difficulty defining the likelihood, choosing the data, and dealing with composite hypotheses—and then says, "It’s not clear to me that Bayesian inference is the right way to attack this sort of problem." That makes the author's stance on the statement most likely opposed, not neutral. · YouCongress gpt-5.4-2026-03-05 · 3mo ago

Quote authenticity verification history

Report this

AI Verified The source URL is fetchable and contains the quote in Andrew Gelman’s post titled “Controversy over different estimates of covid origins probabilities.” The page says it was “Posted on August 1, 2025 … by Andrew,” and the linked author page identifies that author as Andrew Gelman. The quoted text appears in the post body with matching wording, aside from normal typographic differences such as straight vs. curly apostrophes/quotes. The stored author, date (2025-08-01), and source URL are therefore correct. ([statmodeling.stat.columbia.edu](https://statmodeling.stat.columbia.edu/2025/08/01/different-estimates-of-covid-origins-probabilities/)) · YouCongress gpt-5.4-2026-03-05 · 3mo ago

replying to Andrew Gelman

Other opinions from Andrew Gelman

See all

Andrew Gelman votes Against

Bayesian analysis is the right framework for settling the COVID-19 origins question

It's not clear to me that Bayesian inference is the right way to attack this sort of problem. But I’ve been intimidated by the technical biological details in all these analyses so I haven’t looked at them personally.

AI Verified source (Feb 3, 2025)