Timeline for Difference of Gamma random variables
Current License: CC BY-SA 3.0
21 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Mar 28, 2021 at 13:58 | answer | added | Afshin Fallah | timeline score: 0 | |
| Oct 1, 2017 at 15:07 | history | edited | kjetil b halvorsen♦ | CC BY-SA 3.0 |
deleted 7 characters in body
|
| May 20, 2017 at 12:58 | history | edited | kjetil b halvorsen♦ |
edited tags
|
|
| Oct 14, 2016 at 11:38 | answer | added | Nathan Crock | timeline score: 12 | |
| Jun 18, 2016 at 18:14 | comment | added | Felipe G. Nievinski | An interesting special case: math.stackexchange.com/questions/85249/… | |
| Jun 12, 2015 at 8:02 | comment | added | bonanza | maybe this helps: math.kit.edu/stoch/~klar/seite/veroeffentlichungen/media/… | |
| Jan 9, 2014 at 16:27 | vote | accept | FBC | ||
| Mar 28, 2013 at 9:57 | comment | added | Richi W | Just a small remark: for the special case of exponentially distributed rvs with the same parameter the result is Laplace (en.wikipedia.org/wiki/Laplace_distribution). | |
| Jan 25, 2013 at 15:22 | comment | added | whuber♦ | @Dilip Sorry; I missed that--you are correct that you explicitly included the assumption of integrality. However, right up to that point you have only applied the definition of the sum and have not yet actually done any reduction of the problem, so there's still nothing to critique. | |
| Jan 25, 2013 at 15:18 | comment | added | Dilip Sarwate | @whuber I didn't make an implicit assumption; everything that I wrote up to and including the last displayed integral holds for all shape parameters. For the development beyond that I explicitly stated that it applied for the case when the shape parameters are integers. | |
| Jan 25, 2013 at 14:55 | comment | added | whuber♦ | @Dilip You have implicitly assumed both shape parameters are integers; that assumption allows for a huge simplification. | |
| Jan 25, 2013 at 2:56 | comment | added | Dilip Sarwate | @whuber Perhaps you could critique my answer below for the case of different scale factors? | |
| Jan 24, 2013 at 14:37 | answer | added | Dilip Sarwate | timeline score: 27 | |
| S Jan 24, 2013 at 11:16 | history | suggested | Scortchi♦ | CC BY-SA 3.0 |
improved formatting
|
| Jan 24, 2013 at 8:42 | review | Suggested edits | |||
| S Jan 24, 2013 at 11:16 | |||||
| Jan 23, 2013 at 21:41 | comment | added | whuber♦ | There's little hope of deriving anything simple or in closed form unless the two scale factors are the same. | |
| Jan 23, 2013 at 21:41 | comment | added | dimitriy | The Moschopoulos paper claims that the method can be extended to linear combinations, but you are right that the rescaling seems to be restricted to weights greater than 0. I stand corrected. | |
| Jan 23, 2013 at 21:23 | review | First posts | |||
| Jan 23, 2013 at 21:25 | |||||
| Jan 23, 2013 at 21:17 | comment | added | FBC | Unfortunately not relevant, that post considers the weighted sum of Gamma random variables where the weights are strictly positive. In my case the weights would be +1 and -1 respectively. | |
| Jan 23, 2013 at 21:14 | comment | added | dimitriy | I think may be relevant: stats.stackexchange.com/q/2035/7071 | |
| Jan 23, 2013 at 21:08 | history | asked | FBC | CC BY-SA 3.0 |