I thought that a good Bayesian model was supposed to be demonstrably robust under a range of prior distributions?
The Bayesian Cringe (2021)
21–27 of 27 posts
Re: The Bayesian Cringe (2021)
#22Le Cam had interesting comments on Bayesian statistics.
https://errorstatistics.com/2013/11/18/lucien-le-cam-the-bay...
Re: The Bayesian Cringe (2021)
#23I noticed a shift in my attitude in strong priors when I switched from academia to industry and have only recently realized why. When doing an analysis in an academic setting, the goal is to get a paper past reviewers to be published. And the reviewers were adversaries that were trying to disprove your work (at best these were helpful critique; at worst they were bad-faith nit-pickers that were looking for any excuse…
It's funny because there's really no difference between arbitrarily setting priors and arbitrarily selecting a p-value. Both are basically just a line you draw beforehand to see if it gets crossed.
Re: The Bayesian Cringe (2021)
#24There's also the fact that a prior is really hard to explain to someone else. By definition, it's the unexplainable starting point! Yet when I lay out fairly tight Bayesian reasoning, there's always that one person sucking life out of the entire conversation with "Wait can you go back to that first number? How did you arrive at that?" and it's an unanswerable question because any attempt would have to start from anot…
And yet nobody asks "how did you come up with that .05 significance level?"
Re: The Bayesian Cringe (2021)
#25What's the difference between a prior and a bias? How does one distinguish between the two?
You can set your priors equally. 100% / number of possible outcomes.
Re: The Bayesian Cringe (2021)
#26I thought that a good Bayesian model was supposed to be demonstrably robust under a range of prior distributions?
Yes, but a "range of prior distributions" doesn't mean every possible prior distribution. Sometimes, the information in the prior distribution is required to get you to a place where your computational system can efficiently explore a meaningful subspace instead of providing nonsense.
If meaningfully different priors lead to meaningfully different posteriors, you're probably missing something that would either eliminate one of those priors from contention or marry the differing behavior in some unifying explanation/model. Either way is a win in my book; both provide a new direction for research!
Re: The Bayesian Cringe (2021)
#27[dead]