The Volatility Forecasting Power of Financial Network Analysis
Table 8
Forecasts of realized volatility of Asian and Oceania stock market indices 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
NIKKEI—Japan
HANG-SENG—Hong Kong
KOSPI—Korea
TSE—Taiwan
Jakarta stock exchange—Indonesia
KLCI—Malaysia
Strait Times—Singapore
ASX—Australia
NZSE—New Zealand
Panel A VPMFGL model
AR(3)
2.284
3.221
2.478
4.994
−0.467
1.038
1.818
1.938
2.322
AR(6)
1.599
2.691
2.002
5.929
−0.778
1.008
1.649
2.344
3.042
AR(3) VVIX(1)
−0.353
−0.529
−0.374
0.005
−0.282
−0.081
−0.062
−0.268
−0.394
AR(6) VVIX(1)
−0.738
−1.050
−0.607
0.135
0.357
−0.354
−0.152
−0.284
−0.504
Panel B VMSTL model
AR(3)
4.630
3.063
3.268
5.946
−0.484
2.135
2.638
2.958
3.625
AR(6)
3.977
2.469
2.541
6.841
−0.815
2.008
2.268
3.319
4.343
AR(3) VVIX(1)
0.774
−0.621
−0.110
0.104
−0.409
−0.304
0.259
−0.107
−0.447
AR(6) VVIX(1)
0.329
−1.045
−0.515
0.147
0.158
−0.474
0.087
−0.189
−0.538
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.