Timeline for Why is it so cool to square numbers (in terms of finding the standard deviation)?
Current License: CC BY-SA 3.0
33 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Apr 1 at 1:06 | review | Close votes | |||
| Apr 3 at 14:16 | |||||
| Jan 27 at 14:56 | review | Close votes | |||
| Feb 5 at 3:07 | |||||
| Jan 27 at 14:38 | comment | added | David White | I stumbled upon this question while googling something related to a class I am teaching. It's certainly not "research level" and if it was asked today it would have been closed. Future readers should not get inspired to ask similar questions. Back in 2009, the norms on mathoverflow were different. | |
| Mar 6, 2023 at 16:46 | comment | added | Pietro Majer | A general reason is: because squares are round! | |
| Mar 6, 2023 at 16:25 | review | Close votes | |||
| Mar 11, 2023 at 3:08 | |||||
| Mar 6, 2023 at 15:27 | answer | added | devdrc | timeline score: 0 | |
| Nov 28, 2015 at 17:18 | history | edited | user9072 | CC BY-SA 3.0 |
deleted 4 characters in body; edited title
|
| Jul 9, 2015 at 10:17 | answer | added | Aaron Meyerowitz | timeline score: 5 | |
| Mar 24, 2015 at 13:09 | comment | added | Avicenna | I agree it wasnt probably what user 678 was asking for. But the example I gave also gives a physical motivation why you want a measure of deviation which is independent of your coordinate frame and representation of your molecule. | |
| Mar 23, 2015 at 18:34 | comment | added | Michael Hardy | @Avicenna : I think your comment is silly. Obviously the sum of all deviations from the mean is zero. The obvious alternative to squaring the deviations is not just leaving them alone; it's taking their absolute values, since those are the distances from the observations to the mean. | |
| Mar 22, 2015 at 16:32 | comment | added | Avicenna | If you did not square them negative deviations would tend to cancel positive deviations and although you might have alot of deviation from mean you would not see it at all. An example is if you take a molecule near equilibrium and add all its oscillations vectorially they will tend to 0 and you might think that the molecule is not moving at all. But it is vibrating alot and that is reflected by the norm of the vectors that describe the oscillation. Same issue. | |
| Mar 22, 2015 at 16:24 | comment | added | Michael Hardy | I've taken the liberty of inserting the missing term. ${}\qquad{}$ | |
| Mar 22, 2015 at 16:24 | history | edited | Michael Hardy | CC BY-SA 3.0 |
added 12 characters in body
|
| Mar 22, 2015 at 15:16 | comment | added | Yaakov Baruch | In the formula for $\sigma$ above, the term $(2-2.6)^2$ should of course appear twice. | |
| Mar 22, 2015 at 12:47 | history | edited | Qfwfq | CC BY-SA 3.0 |
edited body
|
| Mar 22, 2015 at 10:55 | answer | added | Yaakov Baruch | timeline score: 1 | |
| Mar 22, 2015 at 2:02 | answer | added | Michael Hardy | timeline score: 21 | |
| Jan 14, 2014 at 16:36 | comment | added | isomorphismes | I hope that (over four years later) someone will return to this classical question. There seems to be something special about the number $p=2$ in $L_p$ norms. What is it? Flatness? Something exotic? (whatever makes Gleason's theorem work?) It seems to me that whatever makes $2$ special is independent of the CLT. It would be disappointing if the Gaussian assumption is the final reason for $p=2$. | |
| S Jan 14, 2014 at 16:15 | history | suggested | isomorphismes | CC BY-SA 3.0 |
improved formatting
|
| Jan 14, 2014 at 16:12 | review | Suggested edits | |||
| S Jan 14, 2014 at 16:15 | |||||
| Sep 10, 2011 at 10:16 | answer | added | david | timeline score: -3 | |
| Jul 30, 2010 at 1:22 | answer | added | user8040 | timeline score: 0 | |
| Oct 24, 2009 at 12:10 | answer | added | Darsh Ranjan | timeline score: 13 | |
| Oct 24, 2009 at 10:11 | history | edited | Ilya Nikokoshev |
edited tags
|
|
| Oct 22, 2009 at 19:02 | answer | added | Robert Parviainen | timeline score: 6 | |
| Oct 22, 2009 at 18:07 | comment | added | Ilya Nikokoshev | +1, excellent question, though I think the title can be improved. I think you selected the wrong answer though — there are many better reasons for the deviation formula than convenience. | |
| Oct 19, 2009 at 3:26 | vote | accept | user668 | ||
| Oct 18, 2009 at 22:17 | answer | added | Reid Barton | timeline score: 56 | |
| Oct 18, 2009 at 22:06 | answer | added | Qiaochu Yuan | timeline score: 13 | |
| Oct 18, 2009 at 22:02 | answer | added | Anna Varvak | timeline score: 1 | |
| Oct 18, 2009 at 18:29 | answer | added | John D. Cook | timeline score: -4 | |
| Oct 18, 2009 at 17:17 | answer | added | Mark4483 | timeline score: 24 | |
| Oct 18, 2009 at 16:59 | history | asked | user668 | CC BY-SA 2.5 |