Timeline for Why would initializing an ARMA process in a deterministic way, prevent it from being stationary?
Current License: CC BY-SA 3.0
14 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Apr 13, 2018 at 8:15 | history | edited | Ferdi |
Adding the stationarity tag
|
|
| Apr 13, 2018 at 8:12 | history | edited | kjetil b halvorsen♦ | CC BY-SA 3.0 |
deleted 33 characters in body; edited tags
|
| Mar 14, 2018 at 22:41 | vote | accept | An old man in the sea. | ||
| Mar 13, 2018 at 2:28 | answer | added | Ben | timeline score: 3 | |
| Dec 4, 2016 at 21:02 | comment | added | An old man in the sea. | @RichardHardy No problem, Richard. ;) | |
| Dec 4, 2016 at 17:40 | comment | added | Richard Hardy | Just to let you know -- sorry, I will not read that one soon; working on my own stuff, deadlines approaching... | |
| Dec 4, 2016 at 16:29 | comment | added | An old man in the sea. | @RichardHardy that's the thing. For a given $X_t$, we can find different polynomials and a different white noise, from the original equation, such that $X_t$ is still a solution. Read the notes from staff.fnwi.uva.nl/p.j.c.spreij/onderwijs/master/… If you manage to understand that section, then please help me. ;) thanks | |
| Dec 4, 2016 at 15:57 | comment | added | Richard Hardy | Interesting. I would think that for given $\theta(B)$, $\phi(B)$ and $Z_t$, $\frac{\theta(B)}{\phi(B)}Z_t$ generates a unique $X_t$. Probably $Z_t$ is not fixed and can be any white noise process? | |
| Dec 4, 2016 at 15:42 | comment | added | An old man in the sea. | @RichardHardy In van der vaart time series notes (freely available on the net), page 130, in the section 8.7 on ARMA stability. He writes on this, but I don't understand exactly what he means... | |
| Dec 4, 2016 at 14:28 | comment | added | An old man in the sea. | @RichardHardy I'm saying that $X_t$ is a solution, when $\phi, \theta$ polynomials, and white noise process $Z_t$ are given. | |
| Dec 4, 2016 at 9:56 | history | edited | Richard Hardy | CC BY-SA 3.0 |
added 4 characters in body
|
| Dec 4, 2016 at 9:55 | comment | added | Richard Hardy | Could you give some background? You say $X_t=\frac{\theta(B)}{\phi(B)}Z_t$ is a solution; but with respect to what is it a solution? What is treated as given and what are the variables? | |
| Dec 3, 2016 at 16:20 | history | edited | An old man in the sea. | CC BY-SA 3.0 |
deleted 63 characters in body
|
| Dec 3, 2016 at 14:13 | history | asked | An old man in the sea. | CC BY-SA 3.0 |