Timeline for Likelihood ratio, Wald, and Score are equivalent?

9 events

when toggle format	what		by	license	comment
Apr 25 at 15:59	history	edited	Richard Hardy	CC BY-SA 4.0	deleted 3 characters in body
Sep 19, 2022 at 22:03	vote	accept	Dave
Jul 16, 2022 at 15:00	history	tweeted			twitter.com/StackStats/status/1548321564596154373
Jul 15, 2022 at 16:11	history	edited	Dave	CC BY-SA 4.0	added 2 characters in body
Jul 15, 2022 at 14:57	history	edited	kjetil b halvorsen♦	CC BY-SA 4.0	added 96 characters in body
Feb 13, 2020 at 16:14	comment	added	Dave		"As $n \rightarrow \infty$, the [Wald, likelihood ratio, and Score] tests have certain asymptotic equivalences. For the best-known GLM, the normal linear model, the three types of inference provide identical results." My impression, evidently wrong, was that the three converged as $n \rightarrow \infty$ but differed for finite $n$...except for the normal linear model, where they gave the same results. I think this warrants a new question, but if even the normal linear model only has asymptotic equivalence, what equivalence does the normal linear have that GLM in general lacks?
Feb 13, 2020 at 16:09	comment	added	AdamO		That's absolutely untrue. They are asymptotically equivalent, so unless $n=\infty$, they will differ a little bit. Small $n$? They can differ a LOT.
Feb 13, 2020 at 15:53	answer	added	Christoph Hanck		timeline score: 6
Feb 13, 2020 at 14:41	history	asked	Dave	CC BY-SA 4.0