Timeline for Why is the rank of covariance matrix at most $n-1$?
Current License: CC BY-SA 3.0
13 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Sep 29 at 23:37 | answer | added | statmerkur | timeline score: 1 | |
| Apr 18, 2022 at 15:00 | history | tweeted | twitter.com/StackStats/status/1516069058742996998 | ||
| Mar 31, 2022 at 21:18 | answer | added | Robert Bray | timeline score: -2 | |
| Jan 5, 2020 at 18:06 | answer | added | Mikel | timeline score: 1 | |
| Apr 13, 2017 at 12:44 | history | edited | CommunityBot |
replaced http://stats.stackexchange.com/ with https://stats.stackexchange.com/
|
|
| Oct 16, 2016 at 19:45 | comment | added | user3070752 | Sorry for delay ;) | |
| Oct 16, 2016 at 17:36 | vote | accept | user3070752 | ||
| Nov 5, 2015 at 17:17 | answer | added | amoeba | timeline score: 40 | |
| Oct 25, 2015 at 18:14 | comment | added | user3070752 | @amoeba your example was clear but I can't understand what is the relationship between fitting hyper-plane in your example and covariance matrix? | |
| Oct 25, 2015 at 17:47 | comment | added | amoeba | So you do understand that $n=2$ leads to rank 1 covariance matrix? Okay, let's take $n=3$ points. Can you see that you can always fit them on a 2D plane? | |
| Oct 25, 2015 at 17:44 | history | edited | amoeba | CC BY-SA 3.0 |
tags, title, light editing
|
| Oct 25, 2015 at 17:41 | comment | added | amoeba | To get the intuition, think about $n=2$ points in 3D. What is the dimensionality of the subspace that these points lie in? Can you fit them on a line (1D subspace)? Or do you need a plane (2D subspace)? | |
| Oct 25, 2015 at 17:33 | history | asked | user3070752 | CC BY-SA 3.0 |