Timeline for How to visualize what canonical correlation analysis does (in comparison to what principal component analysis does)?
Current License: CC BY-SA 3.0
22 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Oct 28, 2018 at 12:25 | history | protected | kjetil b halvorsen♦ | ||
| May 21, 2018 at 3:27 | answer | added | idnavid | timeline score: 3 | |
| Jun 21, 2016 at 22:44 | history | edited | ttnphns |
edited tags
|
|
| Aug 29, 2015 at 21:45 | history | edited | amoeba | CC BY-SA 3.0 |
removed an obsolete update
|
| Jul 14, 2015 at 7:31 | answer | added | Gottfried Helms | timeline score: 3 | |
| May 20, 2014 at 16:00 | answer | added | S Chapman | timeline score: 0 | |
| S Sep 4, 2013 at 1:39 | history | bounty ended | Glen_b | ||
| S Sep 4, 2013 at 1:39 | history | notice removed | Glen_b | ||
| S Sep 3, 2013 at 1:25 | history | bounty started | Glen_b | ||
| S Sep 3, 2013 at 1:25 | history | notice added | Glen_b | Reward existing answer | |
| Jul 31, 2013 at 10:18 | history | edited | figure | CC BY-SA 3.0 |
edited body
|
| Jul 31, 2013 at 9:58 | vote | accept | figure | ||
| Jul 29, 2013 at 20:57 | history | edited | ttnphns | CC BY-SA 3.0 |
added 72 characters in body; edited tags; edited title
|
| Jul 28, 2013 at 14:42 | history | tweeted | twitter.com/#!/StackStats/status/361496895039868929 | ||
| Jul 28, 2013 at 14:24 | comment | added | user28555 | Some have suggested to visualize canonical correlations using heliographs. You might want to read the paper ti.arc.nasa.gov/m/profile/adegani/Composite_Heliographs.pdf | |
| Jul 28, 2013 at 13:53 | answer | added | ttnphns | timeline score: 133 | |
| Jul 28, 2013 at 13:16 | history | edited | figure | CC BY-SA 3.0 |
added 56 characters in body
|
| Jul 27, 2013 at 10:48 | comment | added | ttnphns | Well, yes, "related" is better. CCA takes account for both inter-covariances and cross-covariances. | |
| Jul 27, 2013 at 9:25 | comment | added | figure | Well, strictly speaking related might be a better choice of word. Anyway, PCA operates on a covariance matrix, and CCA on a cross-covariance matrix. If you have just one dataset, calculating its cross-covariances against itself end up back to the simpler case (PCA). | |
| Jul 27, 2013 at 5:11 | comment | added | ttnphns | In what way CCA generalizes PCA? I wouldn't say it is its generalization. PCA works with one set of variables, CCA works with two (or more, modern implementations), and this is a major difference. | |
| Jul 26, 2013 at 20:46 | review | First posts | |||
| Jul 26, 2013 at 20:51 | |||||
| Jul 26, 2013 at 20:28 | history | asked | figure | CC BY-SA 3.0 |