| |
 |
|
|
Science Forum Index » Space - Consult Forum » Estimation of Gamma processes
Page 1 of 1
|
| Author |
Message |
| karl |
 Posted: Wed Apr 23, 2008 2:23 am |
|
|
|
Guest
|
I am looking for information how to estimate the parameters of a Gamma
Process from unequally spaced observations
with errors.
I am grateful for any hint.
Thanks
Karl |
|
|
| Back to top |
|
| Herman Rubin |
| Posted: Sun Apr 27, 2008 9:09 pm |
|
|
|
Guest
|
In article <480ee40d$0$23696$9b4e6d93@newsspool2.arcor-online.net>,
karl <oudeis@nononet.com> wrote:
Quote: I am looking for information how to estimate the parameters of a Gamma
Process from unequally spaced observations
with errors.
I am grateful for any hint.
Thanks
Karl
I am not sure what your model is. Without errors, I see
no problem at all, and I am not convinced that it is
any harder with errors if the observations are equally
spaced or not.
What is your probabilistic model?
--
This address is for information only. I do not claim that these views
are those of the Statistics Department or of Purdue University.
Herman Rubin, Department of Statistics, Purdue University
hrubin@stat.purdue.edu Phone: (765)494-6054 FAX: (765)494-0558 |
|
|
| Back to top |
|
| karl |
| Posted: Mon Apr 28, 2008 11:14 pm |
|
|
|
Guest
|
Herman Rubin schrieb:
Quote: In article <480ee40d$0$23696$9b4e6d93@newsspool2.arcor-online.net>,
I am not sure what your model is. Without errors, I see
no problem at all, and I am not convinced that it is
any harder with errors if the observations are equally
spaced or not.
What is your probabilistic model?
The model is that we observe at time points t_1,.. t_n the values of
X(t_i) = S(t_i) + Z(t_i),
where S(t_i) is the value of the gamma process and the Z(t_i) are
i.i.d. zero mean normal rv's with unknown variance.
Further complication is that only positive values of X(t_i) can be
observed. This is a model for detoriation data in pipelines.
Ciao
Karl |
|
|
| Back to top |
|
| |
|
Page 1 of 1
All times are GMT - 5 Hours
The time now is Sun Jul 27, 2008 2:29 am
|
|
