Table 8.

The result of different $k^{max}$values with the MCS test.

Forecasting models	$k^{max}$ = 40				$k^{max}$ = 60
	QLIKE		MSE		QLIKE			MSE
	Range	SeimQ	Range	SeimQ	Range	SeimQ		Range		SeimQ
Panel A: h = 1
MIDAS-RV	0.0782	0.0717	0.8566	0.8566	0.0797	0.0494		0.7775		0.8291
MIDAS-RV-OVX	1.0000	1.0000	1.0000	1.0000	1.0000		1.0000		0.9174		0.9174
MS-MIDAS-RV	0.0782	0.0717	0.2262	0.4248	0.0726	0.0456		0.5142		0.6877
MS-MIDAS-RV-OVX	0.0782	0.0717	0.2262	0.4248	0.1443	0.1443		1.0000		1.0000
Panel B: h = 5
MIDAS-RV	0.0156	0.0199	0.5832	0.5815	0.0451	0.0413		0.3257		0.5056
MIDAS-RV-OVX	0.0156	0.0199	0.0807	0.2118	0.0975	0.0873		0.6544		0.6892
MS-MIDAS-RV	0.2730	0.2730	0.6670	0.6670	0.2739	0.2739		0.7638		0.7638
MS-MIDAS-RV-OVX	1.0000	1.0000	1.0000	1.0000	1.0000	1.0000		1.0000		1.0000
Panel C: h = 20
MIDAS-RV	0.0035	0.0055	0.0118	0.0411	0.0026	0.0024		0.0062		0.0068
MIDAS-RV-OVX	0.0057	0.0088	0.0118	0.0306	0.0044	0.0034		0.0062		0.0094
MS-MIDAS-RV	0.0898	0.0898	1.0000	1.0000	1.0000	1.0000		0.3258		0.3258
MS-MIDAS-RV-OVX	1.0000	1.0000	0.6003	0.6003	0.7120	0.7120		1.0000		1.0000

Notes: This table exhibits models’ MCS p-values. The forecasts for different horizons h = 1, 5, 20 are shown in Panel A, B, C, and the different $k^{max}$(40, 60) are shown in different columns. In this table, the MCS test p-value of 1indicates a better prediction.