Timeline for Is bootstrapping inherently Frequentist? If so, how do we do a Bayesian non-parametric two-sample test?
Current License: CC BY-SA 4.0
4 events
when toggle format | what | by | license | comment | |
---|---|---|---|---|---|
May 3 at 9:12 | comment | added | Amorphia | Thanks, both these comments were useful, especially the link - it seems this is a thing, just a bit niche. | |
May 1 at 19:20 | comment | added | Xi'an | Check stats.stackexchange.com/q/447532/7224 | |
May 1 at 10:45 | comment | added | Christian Hennig | Theoretical justification for the bootstrap in frequentist analysis isn't exactly a piece of cake, and I remember I have seen asymptotical results that looked like it would need very similar assumptions to the Central Limit Theorem to work - which is the same situation in which a standard t-test will work as well (for large enough samples such as 2*500 appeal to the CLT is fine and there's not much worry about non-normality, unless there's worry for the bootstrap, too). | |
May 1 at 7:40 | history | asked | Amorphia | CC BY-SA 4.0 |