The Volatility Forecasting Power of Financial Network Analysis
Table 7
Forecasts of European realized stock market indices volatility using out-of-sample analysis with monthly data (π ≡ P/R = 0.4).
(1)
(2)
(3)
(4)
(5)
(6)
(7)
(8)
(9)
(10)
Benchmark model
FTSE—UK
CAC—France
DAX—Germany
IBEX—Spain
FTSEMIB—Italy
AEX—Holland
OMX—Sweden
RTS—Russia
SMI—Swiss
Panel A VPMFGL model
AR(3)
0.107
1.159
0.218
0.708
3.079
−0.907
1.240
−0.601
1.208
AR(6)
−0.104
0.976
0.100
0.460
2.766
−1.086
0.360
−0.647
1.172
AR(3) VVIX(1)
−0.533
−0.049
−0.941
−0.353
0.602
−1.828
−0.411
−0.282
−0.543
AR(6) VVIX(1)
−0.667
−0.425
−1.071
−0.732
−0.004
−2.025
−0.866
−0.332
−0.730
Panel B VMSTL model
AR(3)
0.883
2.743
1.394
2.151
4.371
0.672
2.747
−0.623
2.617
AR(6)
0.608
2.609
1.260
2.150
4.213
0.526
1.872
−0.733
2.522
AR(3) VVIX(1)
−0.325
1.048
−0.233
0.747
1.333
−0.886
0.034
−0.722
0.043
AR(6) VVIX(1)
−0.531
0.682
−0.310
0.468
0.718
−1.090
−0.516
−0.871
−0.135
10%, 5%, and 1% critical values are 0.685, 1.079, and 2.098, respectively, when there is only one excess parameter. P represents the number of one-step-ahead forecasts and R the sample size of the first estimation window. The AR(3)-VVIX(1) benchmark corresponds to model 1. ,, and . Source: authors’ elaboration.