Timeline for refrence for simple statistics question: estimation of variance of $n$, for known $r=s+n$, for $s= \pm1$, $n=N(0,\sigma)$
Current License: CC BY-SA 3.0
5 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Dec 12, 2011 at 16:31 | comment | added | psd | @Alexander: Regarding statistical efficiency and consistency, I think that while both this answer and the answer given by Hahn are statistically consistent, I think that only this answer is asymptotically efficient. I don't have a proof of this, but my reasoning is that Hahn's answer goes through a statistic (proportion of data in [-1,1]) that is not statistically sufficient whereas MLE can be proved to be asymptotically efficient in certain well-behaved situations. | |
| Dec 12, 2011 at 16:08 | comment | added | psd | @Alexander: Edited to add wiki links. | |
| Dec 12, 2011 at 16:04 | history | edited | psd | CC BY-SA 3.0 |
added 290 characters in body
|
| Dec 11, 2011 at 13:33 | comment | added | Alexander Chervov | Thank You that is good idea, I also thought that kind of soft-estimate is relevant, I did not tried it, since time lacking... Can You suggest some refrence on "expectation-maximization" ? Something very very introductory ? | |
| Dec 9, 2011 at 22:01 | history | answered | psd | CC BY-SA 3.0 |