Timeline for Applying ARIMA to time series data
Current License: CC BY-SA 3.0
3 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Nov 6, 2017 at 17:46 | comment | added | Djones4822 | Right but there's no reasonable assumption for a (1,1,1) specification. Further, if the (1,1,1) is returning a similar RMSE to the (1,0,0), and the AIC/BIC is similar, then why add additional insignificant regressors? The model output highlights the statistical insignificance as well. I think what you're seeing is the result of improper model specification. | |
| Nov 6, 2017 at 17:37 | comment | added | RPT | I tried using just an AR(1) model with the data, but it more or less gives me the same forecast as I have now. | |
| Nov 6, 2017 at 17:34 | history | answered | Djones4822 | CC BY-SA 3.0 |