Timeline for Large sample asymptotic/theory - Why to care about?
Current License: CC BY-SA 3.0
11 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Feb 6, 2023 at 3:44 | comment | added | kjetil b halvorsen♦ | Also stats.stackexchange.com/questions/183813/… | |
| Mar 20, 2017 at 9:33 | history | edited | kjetil b halvorsen♦ | CC BY-SA 3.0 |
deleted 42 characters in body
|
| Jun 27, 2013 at 15:47 | vote | accept | Sam | ||
| Jun 21, 2013 at 0:30 | comment | added | StasK | For binomial distribution, $n>30$ is a poor criterion. If you have $p=0.001$ and $n=30$, the mean = 0.03 and s.d. = 0.173, so at the face value, the probability that the binomial variable is below zero via normal approximation is 43%, which is hardly an acceptable approximation for zero. Better rules suggest $n \min( p, 1-p) > 15$, and they account for these higher order issues. | |
| Jun 21, 2013 at 0:24 | comment | added | StasK | You should start reading on higher order asymptotics, as you apparently are only familiar with the first order asymptotic normality and such; with that, you don't yet know everything about the asymptotic behavior. It's like saying, "I know that $sin x=x$; why does everybody say sine is periodic???". | |
| S Jun 21, 2013 at 0:23 | history | suggested | Nameless | CC BY-SA 3.0 |
corrected one sentence
|
| Jun 20, 2013 at 23:37 | review | Suggested edits | |||
| S Jun 21, 2013 at 0:23 | |||||
| Jun 20, 2013 at 23:35 | answer | added | Nameless | timeline score: 8 | |
| May 5, 2013 at 1:59 | history | tweeted | twitter.com/#!/StackStats/status/330864341995892736 | ||
| May 4, 2013 at 20:01 | comment | added | Danica | Large-sample behavior is one way to show that a given estimator works, or whatever else, in the limit of infinite data. You're right that it doesn't necessarily tell us anything about how good an estimator is in practice, but it's a first step: you'd be unlikely to want to use an estimator that's not asymptotically consistent (or whatever). The advantage of asymptotic analysis is that it's often easier to figure out than a finite-sample one. | |
| May 4, 2013 at 19:38 | history | asked | Sam | CC BY-SA 3.0 |