Timeline for Constructing a continuous distribution to match $m$ moments
Current License: CC BY-SA 3.0
10 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Nov 17, 2022 at 8:59 | comment | added | Ismail Chamseddine | My book (PhD thesis, Imperial College, 1997, Construction of Random signals from their Higher Order Moments: Applications in Signal Processing and Mathematical Logic) is just about this. Hope this is helping you. | |
| Dec 9, 2019 at 13:20 | history | edited | kjetil b halvorsen♦ |
edited tags
|
|
| S Nov 21, 2016 at 13:51 | history | suggested | Davide Giraudo | CC BY-SA 3.0 |
fixed Latex.
|
| Nov 21, 2016 at 13:12 | review | Suggested edits | |||
| S Nov 21, 2016 at 13:51 | |||||
| Nov 21, 2016 at 13:03 | answer | added | julyan | timeline score: 14 | |
| Apr 9, 2015 at 20:33 | history | tweeted | twitter.com/#!/StackStats/status/586265628346097664 | ||
| Mar 26, 2015 at 19:09 | comment | added | Anthony | Most of your requirements/preferences could be satisfied by Headrick's (2002) 5th order polynomial family, but it will only work for m < 7. I'm curious to know if you find a satisfactory solution there or elsewhere. Reference: Headrick, T. (2002). Fast fifth-order polynomial transforms for generating univariate and multivariate nonnormal distributions. Computational Statistics & Data Analysis, 40, 685-711. | |
| Mar 15, 2015 at 6:24 | comment | added | andrewH | I'm interested in systems of distributions in which n-1 parameter distributions are related to n-parameter distributions by nesting, and in which distributions are built up from zero-parameter distributions like the standard normal or the standard gamma by invertible transformations of the variable and the additional parameter: x+c, x*c, x^c, e^cx, and the like. I find the ability to elaborate or simplify distributions in this way an appealing property. I think of this problem analogously, since a distribution that can take arbitrary values for the m moments will require m coefficients. | |
| Mar 13, 2015 at 19:30 | comment | added | whuber♦ | Of interest is Mead and Papanicolaou, Maximum entropy in the problem of moments. J. Math. Phys. 25, 2404 (1984). I don't follow the meaning of anything in your penultimate paragraph, though. | |
| Mar 13, 2015 at 18:27 | history | asked | andrewH | CC BY-SA 3.0 |