Table 11.
Results of MCS test with controlling VIX.
Forecasting models | QLIKE |
MSE |
||
---|---|---|---|---|
Range | SeimQ | Range | SeimQ | |
Panel A: h = 1 | ||||
MIDAS-RV-VIX | 1.0000 | 1.0000 | 0.2687 | 0.1584 |
MIDAS-RV-OVX-VIX | 0.1242 | 0.1170 | 0.2687 | 0.1584 |
MS-MIDAS-RV-VIX | 0.1242 | 0.1170 | 0.1675 | 0.1584 |
MS-MIDAS-RV-OVX-VIX | 0.0929 | 0.0455 | 1.0000 | 1.0000 |
Panel B: h = 5 | ||||
MIDAS-RV-VIX | 0.1208 | 0.0847 | 0.1956 | 0.1262 |
MIDAS-RV-OVX-VIX | 0.1208 | 0.0637 | 0.1956 | 0.1262 |
MS-MIDAS-RV-VIX | 1.0000 | 1.0000 | 0.1956 | 0.1262 |
MS-MIDAS-RV-OVX-VIX | 0.6072 | 0.6072 | 1.0000 | 1.0000 |
Panel C: h = 20 | ||||
MIDAS-RV-VIX | 0.0110 | 0.0047 | 0.2155 | 0.1613 |
MIDAS-RV-OVX-VIX | 0.0189 | 0.0170 | 0.2155 | 0.2175 |
MS-MIDAS-RV-VIX | 0.5544 | 0.5544 | 1.0000 | 1.0000 |
MS-MIDAS-RV-OVX-VIX | 1.0000 | 1.0000 | 0.7108 | 0.7108 |
Notes: This table exhibits models’ MCS p-values by adding VIX index, which is constructed similar with OVX. The forecasts for different horizons h = 1, 5 and 20 are shown in Panel A, B, C. In this table, the MCS test p-value of 1indicates a better prediction.