Forecast point estimates and mean squared errors
| Time | SETAR | AR | Observed |
|---|---|---|---|
| 2016q1 | 0.096 | −0.062 | 0.137 |
| 2016q2 | −0.102 | 0.043 | −0.163 |
| 2016q3 | −0.172 | −0.097 | −0.093 |
| 2016q4 | 0.193 | 0.097 | 0.104 |
| 2017q1 | −0.009 | −0.003 | 0.022 |
| 2017q2 | 0.148 | 0.002 | −0.072 |
| 2017q3 | −0.14 | −0.029 | −0.233 |
| 2017q4 | 0.108 | 0.039 | 0.115 |
| Forecast RMSE | 0.099 | 0.13 | |
| Mean absolute error | 0.078 | 0.099 |
| Time | SETAR | AR | Observed |
|---|---|---|---|
| 2016q1 | 0.096 | −0.062 | 0.137 |
| 2016q2 | −0.102 | 0.043 | −0.163 |
| 2016q3 | −0.172 | −0.097 | −0.093 |
| 2016q4 | 0.193 | 0.097 | 0.104 |
| 2017q1 | −0.009 | −0.003 | 0.022 |
| 2017q2 | 0.148 | 0.002 | −0.072 |
| 2017q3 | −0.14 | −0.029 | −0.233 |
| 2017q4 | 0.108 | 0.039 | 0.115 |
| Forecast RMSE | 0.099 | 0.13 | |
| Mean absolute error | 0.078 | 0.099 |
Note(s): AR = autoregressive model, SETAR = selfexciting threshold autoregressive model, RMSE = root mean square error
Sharing content requires targeting cookies to be enabled. Please update your cookie preferences to use this feature.