Timeline for Alternatives to Bayesian statistics when distributions are unknown
Current License: CC BY-SA 4.0
14 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Jun 22, 2021 at 16:48 | answer | added | rep_ho | timeline score: 3 | |
| Jun 22, 2021 at 12:27 | answer | added | Soleil | timeline score: 0 | |
| Jun 21, 2021 at 23:13 | comment | added | Captain Emacs | @Acccumulation Even assuming you could do it in practice, you still have heavy dependence on the choice of computer/programming language. Unfortunately, that issue is not going to go away (I think Hutter around 2016 had a discussion of that). | |
| Jun 21, 2021 at 14:09 | comment | added | wizzwizz4 | @Acccumulation In practice, the assumptions that that prior distribution makes aren't worth having. (It assumes integers are much more likely than reals, for instance, but most things you do stats on involve reals.) | |
| Jun 21, 2021 at 14:05 | comment | added | Acccumulation |
Just list every computer program that can generate a probability distribution, give each one a prior of 2^-(number of bits+1), calculate the likelihood of the data for each one, then update. Simple!
|
|
| Jun 21, 2021 at 11:28 | vote | accept | stevew | ||
| Jun 21, 2021 at 11:02 | comment | added | stevew | Thanks for your replies @BruceET and Dave, will have a read of that paper. I suppose I can choose a non-informative prior, but I'd still need to choose a likelihood distribution, which for a regression, it's likely going to be Gaussian? | |
| Jun 20, 2021 at 14:25 | history | became hot network question | |||
| Jun 20, 2021 at 12:00 | history | tweeted | twitter.com/StackStats/status/1406582617768595459 | ||
| Jun 20, 2021 at 9:02 | answer | added | Xi'an | timeline score: 24 | |
| Jun 20, 2021 at 7:25 | comment | added | Dave | Following @BruceET’s comment, John Kruschke’s “Bayesian Estimation Supersedes the t-test” (BEST) paper used t-distributed priors for that purpose. (As a tangent, Kruschke is a member on here and once answered a question I had about that BEST paper!) | |
| Jun 20, 2021 at 7:19 | comment | added | BruceET | You might want a non-informative prior distribution. One choice might be a normal distribution with a mean that is near a plausible population mean and a huge standard deviation. Or a gamma distribution with very small shape and rate parameters. Then the posterior distribution will depend mainly on your data. | |
| Jun 20, 2021 at 7:18 | answer | added | Tim | timeline score: 18 | |
| Jun 20, 2021 at 6:20 | history | asked | stevew | CC BY-SA 4.0 |