Timeline for What common forecasting models can be seen as special cases of ARIMA models?
Current License: CC BY-SA 4.0
13 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| S Mar 4, 2022 at 6:06 | history | suggested | feetwet | CC BY-SA 4.0 |
Copy edited
|
| Mar 4, 2022 at 2:31 | review | Suggested edits | |||
| S Mar 4, 2022 at 6:06 | |||||
| Jul 16, 2013 at 17:26 | comment | added | Olga Mu | Auto.arima in the forecast package helps a lot with identifying the proper model. It really helps to try outsome things and see how they perform. | |
| Mar 7, 2012 at 9:20 | vote | accept | Bruder | ||
| Feb 29, 2012 at 21:37 | comment | added | IrishStat | @Bruder To fit a simple least squares line through your data points , use a multivariate version of Box-Jenkins. Create a dummy variable x having the values 1,2,3...n and then estimate a Transfer Function with no ARIMA structure and a constant and a polynomial on x that just has one numerator polynomial with 1 coefficient with a backorder power of 0 . In terms of tour moving average window, you need to learn how to identify an ARIMA model or use software that does that and shows you the steps by which it identifies the correct ARIMA model.Your questions require some form of training to answer | |
| Feb 29, 2012 at 16:06 | comment | added | cardinal |
IrishStat, if you want to signal a user, it's best to use @ instead of :. That way they'll actually receive a notification. Cheers. :)
|
|
| Feb 29, 2012 at 16:00 | comment | added | Bruder | Ok, so to fit a simple least-squares line through the points in my scatterplot all I need is an ARIMA(1,0,0) model? If so I'll add it to the list above. And what about moving average? Is it simply an ARIMA(0,0,1)? If so, how do I choose the width of the moving average window? And what is the difference between an ARIMA(0,0,1) and an ARIMA(0,0,1) with constant. Again, I'm sorry if the answer seems obvious to everyone but me :) | |
| Feb 29, 2012 at 15:35 | comment | added | IrishStat | :zbicylist Correct, since this is a special case of a Transfer Function where there are no user specified inputs and the form of the ARIMA model is (1,0,0) and the model assumes that there are no deterministic variables to be empirically identified ( such as Pulses, level Shifts , Seasonal Pulses and/or Local Time Trends via Intervention Detection . | |
| Feb 29, 2012 at 14:24 | comment | added | zbicyclist | Isn't ARIMA(1,0,0) a regression model where Y = a + b Y_t-1? | |
| Feb 29, 2012 at 14:15 | comment | added | IrishStat | :Bruder A Transfer Function (multivariate Box-Jenkins) can have a PDL(polynomial distributed lag) structure on user-specified input series with an ARIMA component reflecting user-omitted stochastic input series.If you eliminate the ARIMA component you have a lagged regression structure. Often one needs to render the error variance homoegenous via either power transforms (e.g. logs ) or weighted least squares where weights are applied (GLS).These are easily handled via Box-Jenkins.Note that a Log Transform does not ALWAYS deal with data that is fundamentally a multiplicative model. | |
| Feb 29, 2012 at 13:45 | comment | added | Bruder | I lost you here: "it can reduce to a standard regression model by omitting the ARIMA component and assuming a set of weights needed to homogenize the error structure". Otherwise thank you for your answer and link. Also, can't multiplicative models be mimicked via a log trasformation? I read somewhere (bottom of the page) that logging can help in this regard. | |
| Feb 29, 2012 at 13:30 | history | edited | IrishStat | CC BY-SA 3.0 |
added 232 characters in body
|
| Feb 29, 2012 at 13:22 | history | answered | IrishStat | CC BY-SA 3.0 |