Timeline for What subset of ARMA(1,1) processes can be represented as AR(1) - a query about the logic in this derivation
Current License: CC BY-SA 4.0
9 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Nov 27, 2020 at 6:00 | history | tweeted | twitter.com/StackStats/status/1332202517850173441 | ||
| Nov 24, 2020 at 22:26 | comment | added | hydrologist | @JarleTufto - thank you for that. You are indeed correct and so I have modified my title. However, just your prompt has been incredibly helpful. Thank you!\ | |
| Nov 24, 2020 at 22:25 | history | edited | hydrologist | CC BY-SA 4.0 |
edited title
|
| Nov 24, 2020 at 14:26 | vote | accept | hydrologist | ||
| Nov 24, 2020 at 12:34 | answer | added | Jarle Tufto | timeline score: 2 | |
| Nov 24, 2020 at 11:53 | comment | added | Jarle Tufto | I think the title of your question is a bit misleading in that the question asked by Granger and Morris is what subset of ARMA(1,1) processes can be represented as AR(1) + white noise, not the other way around (as all AR(1) + white noise process can be represented as ARMA(1,1)). | |
| Nov 23, 2020 at 23:13 | comment | added | hydrologist | Doesn't it just mean that c > d ? | |
| Nov 23, 2020 at 23:03 | comment | added | hydrologist | I assume that I know c = a (because it is obvious) and then if I have an ARMA(1,1) process I can find its ACF and then from ACF at lag 1 I can find d... so I can find the two parameters - the only question remaining is whether this combination of c and d is a valid way to represent AR(1) + WN as ARMA(1,1) ? | |
| Nov 23, 2020 at 22:34 | history | asked | hydrologist | CC BY-SA 4.0 |