Timeline for Why is the pearson correlation between the 40 and 60 percentile much lower than with the full range?
Current License: CC BY-SA 3.0
14 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Mar 15, 2016 at 12:19 | answer | added | mox | timeline score: 1 | |
| Feb 26, 2016 at 22:14 | comment | added | whuber♦ | For an illustrated example of this phenomenon, please see stats.stackexchange.com/questions/13314/…. | |
| Feb 26, 2016 at 22:12 | vote | accept | Pablo Fleurquin | ||
| Feb 26, 2016 at 21:22 | comment | added | Pablo Fleurquin | @NickCox which one the one from Robert? | |
| Feb 26, 2016 at 20:56 | comment | added | Nick Cox | See now the full answer below. | |
| Feb 26, 2016 at 20:53 | answer | added | Robert Alan Greevy Jr PhD | timeline score: 4 | |
| Feb 26, 2016 at 20:10 | comment | added | Pablo Fleurquin | Hey @NickCox I follow your sugesstion to see the behavior when approaching the medians limit and now I´m more confused :/. The drop in the coefficient happens at the first iteration, droping values outside [1,99] percentile! Any help is appreciated here :) | |
| Feb 26, 2016 at 20:07 | history | edited | Pablo Fleurquin | CC BY-SA 3.0 |
added 498 characters in body
|
| Feb 26, 2016 at 19:46 | comment | added | Nick Cox | Why not reduce the scatter to the two medians? What happens to the correlation as you approach that limit? | |
| Feb 26, 2016 at 19:43 | comment | added | Pablo Fleurquin | Hi @NickCox I will. Anyway I suspect that you think that it is totally ok with your expectations these results. If so, why? | |
| Feb 26, 2016 at 19:28 | comment | added | Nick Cox | Plot what you did to get intuition here. | |
| Feb 26, 2016 at 19:22 | history | undeleted | Pablo Fleurquin | ||
| Feb 26, 2016 at 19:22 | history | deleted | Pablo Fleurquin | via Vote | |
| Feb 26, 2016 at 19:21 | history | asked | Pablo Fleurquin | CC BY-SA 3.0 |