
中国股市波动率预测研究: 基于实时已实现EGARCH-MIDAS模型
Forecasting Chinese Stock Market Volatility: A Real-Time Realized EGARCH-MIDAS Model
本文构建了一个能够充分捕获高频数据信息、当前收益率信息以及波动率长记忆性的实时已实现EGARCH-MIDAS (RT-REGARCH-MIDAS) 模型对中国股市波动率进行建模和预测. 采用上证综合指数(SSEC) 和深证成份指数(SZSEC) 5分钟高频数据进行实证研究, 结果表明: RT-REGARCH-MIDAS模型相比其它众多竞争模型具有更好的收益率数据拟合效果, 能够更好地描述股市波动性. 利用稳健的损失函数以及模型置信集(MCS) 检验作为判断准则, 实证比较了该模型与其它竞争模型对中国股市波动率的样本外预测能力. 实证结果表明: 捕获高频数据信息、当前收益率信息和波动率长记忆性对于股市波动率预测具有重要作用; 在众多竞争模型中, RT-REGARCH-MIDAS模型具有最为优越的波动率预测能力. 进一步, 采用不同的已实现测度、不同的预测窗口、不同的MIDAS滞后阶数、不同的预测期以及样本外R2检验进行稳健性检验, 证实了该模型优越的波动率预测能力具有稳健性. 最后, 通过考察模型波动择时策略发现, 该模型能够获得相比其它模型显著更高的投资组合经济价值.
This paper proposes the real-time Realized EGARCH-MIDAS (RT-REGARCH-MIDAS) model which adequately captures the information content of high-frequency data, the current return information and the long memory of volatility to model and forecast Chinese stock market volatility. An empirical analysis based on the 5-minute high-frequency data of the Shanghai Stock Exchange Composite Index (SSEC) and the Shenzhen Stock Exchange Component Index (SZSEC) shows that the RT-REGARCH-MIDAS model outperforms a variety of competitor models in fitting the return data and can describe the stock market volatility better. Using robust loss functions and the model confidence set (MCS) test, the paper compares the out-of-sample forecasting ability of the model and other competitor models for Chinese stock market volatility. Our empirical results show that accounting for the information content of high-frequency data, the current return information and the long memory of volatility plays an important role in forecasting stock market volatility. As a consequence, the proposed RT-REGARCH-MIDAS model performs the best in forecasting Chinese stock market volatility. Further, according to the robustness checks, the superior volatility forecasting ability of the model is robust to alternative realized measure, alternative forecast windows, alternative MIDAS lags, alternative forecasting horizons and out-of-sample R2 test. Finally, a volatility timing strategy shows that the proposed model yields more significant economic value of portfolio compared to the other models.
波动率预测 / 高频数据信息 / 当前收益率信息 / 波动率长记忆性 / 波动择时 {{custom_keyword}} /
volatility forecasting / information content of high-frequency data / current return information / long memory volatility / volatility timing {{custom_keyword}} /
表1 SSEC和SZSEC指数日度收益率和RV的描述性统计量 |
SSEC | SZSEC | ||||||
收益率 | RV | log-RV | 收益率 | RV | log-RV | ||
均值 | 0.0002 | 0.0002 | 0.0003 | 0.0002 | |||
最小值 | 0.0000 | 0.0000 | |||||
最大值 | 0.0903 | 0.0039 | 0.0916 | 0.0053 | |||
标准差 | 0.0155 | 0.0003 | 1.0262 | 0.0180 | 0.0003 | 0.9506 | |
偏度 | 6.0055 | 0.5530 | 5.7511 | 0.3732 | |||
峰度 | 7.9211 | 58.6474 | 3.0746 | 6.1537 | 56.7239 | 3.1590 | |
Jarque-Bera | 4658.4755 | 590517.3214 | 223.8753 | 1997.2329 | 549880.2496 | 106.0759 | |
37.6847 | 10586.6970 | 23189.0082 | 33.1335 | 8780.2091 | 20829.5662 | ||
68.9416 | 17118.2262 | 40987.1194 | 49.4201 | 14130.7314 | 36288.0783 |
注: |
表2 参数估计结果: SSEC |
GARCH | GJR-GARCH | EGARCH | REGARCH | REGARCH-MIDAS | RT-GARCH | RT-REGARCH-MIDAS | |
0.0002 | 0.0001 | 0.0001 | 0.0003 | 0.0001 | 0.0007 | 2.1006 | |
(0.0002) | (0.0002) | (0.0002) | (0.0002) | (0.0002) | (0.0002) | (6.2843 | |
1.1710 | 1.2005 | ||||||
(1.8237 | (1.6821 | (0.0009) | (0.0017) | (0.0027) | (8.2172 | (0.0084) | |
0.8503 | 0.6764 | ||||||
(0.0017) | (0.0025) | ||||||
12.6342 | 23.0512 | ||||||
(0.0320) | (0.0685) | ||||||
0.0675 | 0.0654 | 0.1584 | 0.3443 | 0.3551 | 0.0500 | 0.4274 | |
(0.0031) | (0.0048) | (0.0033) | (0.0041) | (0.0052) | (0.0087) | (0.0052) | |
0.9304 | 0.9296 | 0.9907 | 0.9684 | 0.7992 | 0.9124 | 0.8897 | |
(0.0028) | (0.0032) | (0.0004) | (0.0007) | (0.0049) | (0.0104) | (0.0045) | |
9.9326 | 0.0829 | ||||||
(9.1063 | (0.0025) | ||||||
0.0052 | |||||||
(0.0052) | (0.0024) | ||||||
(0.0024) | (0.0038) | (0.0029) | |||||
0.0680 | 0.0760 | 0.0313 | |||||
(0.0019) | (0.0026) | (0.0016) | |||||
(0.0051) | (0.0028) | (0.0073) | |||||
0.2270 | 0.2214 | 0.2661 | |||||
(0.0041) | (0.0037) | (0.0046) | |||||
(0.0038) | (0.0042) | (0.0039) | |||||
0.0891 | 0.0886 | ||||||
(0.0020) | (0.0022) | (0.0020) | |||||
| 12721.5178 | 12721.7284 | 12726.0665 | 12805.1984 | 12822.2532 | 12811.3589 | 13507.8648 |
9842.0027 | 9913.7527 | 10195.6116 |
注: () 中是极大似然估计的渐近标准误差, ℓ(r) 是关于收益率的局部极大对数似然值, ℓ(r, x) 是全极大对数似然值. |
表3 参数估计结果: SZSEC |
GARCH | GJR-GARCH | EGARCH | REGARCH | REGARCH-MIDAS | RT-GARCH | RT-REGARCH-MIDAS | |
| 0.0003 | 0.0002 | 0.0002 | 0.0003 | 0.0002 | ||
(0.0002) | (0.0002) | (0.0002) | (0.0002) | (0.0002) | (0.0002) | (8.9252 | |
| 2.8492 | 3.1089 | |||||
(3.6780 | (3.9428 | (0.0014) | (0.0025) | (0.0081) | (1.2426 | (0.0093) | |
| 0.8490 | 0.8905 | |||||
(0.0016) | (0.0045) | ||||||
| 21.3230 | 10.4424 | |||||
(0.0535) | (0.0360) | ||||||
| 0.0596 | 0.0540 | 0.1405 | 0.3400 | 0.3421 | 0.0254 | 0.4150 |
(0.0032) | (0.0052) | (0.0037) | (0.0041) | (0.0053) | (0.0070) | (0.0046) | |
| 0.9322 | 0.9294 | 0.9877 | 0.9628 | 0.7732 | 0.9549 | 0.8905 |
(0.0033) | (0.0041) | (0.0001) | (0.0004) | (0.0051) | (0.0082) | (0.0045) | |
| 1.2292 | 0.0743 | |||||
(1.3261 | (0.0026) | ||||||
| 0.0146 | ||||||
(0.0062) | (0.0027) | ||||||
| |||||||
(0.0028) | (0.0040) | (0.0033) | |||||
| 0.0642 | 0.0736 | 0.0315 | ||||
(0.0019) | (0.0022) | (0.0033) | |||||
| |||||||
(0.0085) | (0.0058) | (0.0060) | |||||
| 0.2212 | 0.2134 | 0.2548 | ||||
(0.0041) | (0.0041) | (0.0063) | |||||
| | ||||||
(0.0038) | (0.0045) | (0.0020) | |||||
| 0.0830 | 0.0833 | |||||
(0.0119) | (0.0022) | (0.0033) | |||||
11846.0918 | 11847.6597 | 11853.9636 | 11935.4139 | 11946.4255 | 11924.3818 | 12530.3081 | |
| 9029.6284 | 9118.9081 | 9320.1459 |
注: ()中是极大似然估计的渐近标准误差, |
表4 波动率预测评价结果 |
SSEC | SZSEC | ||||
MSE | QLIKE | MSE | QLIKE | ||
GARCH | 1.0852 | 2.8992 | |||
GJR-GARCH | 1.0681 | 2.9228 | |||
EGARCH | 9.9715 | 2.8881 | |||
REGARCH | 7.8829 | 2.1432 | |||
REGARCH-MIDAS | 6.8990 | 1.9718 | |||
RT-GARCH | 8.7940 | 2.5157 | |||
RT-REGARCH-MIDAS | 6.5041 | 1.9315 |
注: 表中加粗的数字表示最低损失值. MSE是均方误差, QLIKE是拟似然误差. |
表5 MCS检验结果 |
SSEC | SZSEC | ||||
MSE | QLIKE | MSE | QLIKE | ||
GARCH | 0.0000 | 0.0000 | 0.0000 | 0.0000 | |
GJR-GARCH | 0.0000 | 0.0000 | 0.0000 | 0.0000 | |
EGARCH | 0.0000 | 0.0000 | 0.0000 | 0.0000 | |
REGARCH | 0.0207 | 0.0167 | 0.1303 | 0.2529 | |
REGARCH-MIDAS | 0.0479 | 0.2410 | 0.6024 | 0.9588 | |
RT-GARCH | 0.0000 | 0.0000 | 0.0025 | 0.0000 | |
RT-REGARCH-MIDAS | 1.0000 | 1.0000 | 1.0000 | 1.0000 |
注: 表中数字是MCS检验p值. p值大于0.1 (加粗的数字) 表示模型包含在MCS中, 即预测能力较好的模型. MSE是均方误差, QLIKE是拟似然误差. |
表6 波动率预测评价结果: 不同已实现测度(RRV) |
SSEC | SZSEC | ||||
MSE | QLIKE | MSE | QLIKE | ||
GARCH | 1.0852 | -8.2994 | 2.8992 | ||
GJR-GARCH | 1.0681 | 2.9228 | |||
EGARCH | 9.9715 | 2.8881 | |||
REGARCH | 9.1853 | 2.5259 | |||
REGARCH-MIDAS | 7.9333 | 2.2914 | |||
RT-GARCH | 8.7940 | 2.5157 | |||
RT-REGARCH-MIDAS | 7.0140 | 2.1275 |
注: MSE是均方误差, QLIKE是拟似然误差. MCS检验p值大于0.1 (加粗的数字)表示模型包含在MCS中, 即预测能力较好的模型. |
表7 波动率预测评价结果: 不同预测窗口 |
SSEC | SZSEC | ||||
MSE | QLIKE | MSE | QLIKE | ||
预测窗口: 120天 | |||||
GARCH | 4.2739 | 1.0924 | |||
GJR-GARCH | 4.2473 | 1.0668 | |||
EGARCH | 4.3321 | 1.1356 | |||
REGARCH | 3.6882 | 9.6648 | |||
REGARCH-MIDAS | 3.2960 | 8.6530 | |||
RT-GARCH | 4.1521 | 9.7807 | |||
RT-REGARCH-MIDAS | 3.0339 | 7.0412 | |||
预测窗口: 240天 | |||||
GARCH | 1.2373 | 2.6001 | |||
GJR-GARCH | 1.2358 | 2.5949 | |||
EGARCH | 1.1713 | 2.5513 | |||
REGARCH | 9.1924 | 2.0720 | |||
REGARCH-MIDAS | 7.6334 | 1.8021 | |||
RT-GARCH | 9.8656 | 2.3415 | |||
RT-REGARCH-MIDAS | 7.4869 | 1.6808 | |||
预测窗口: 480天 | |||||
GARCH | 8.3299 | 2.1939 | |||
GJR-GARCH | 8.3128 | 2.2005 | |||
EGARCH | 8.3048 | 2.2585 | |||
REGARCH | 6.7252 | 1.8248 | |||
REGARCH-MIDAS | 5.6935 | 1.5793 | |||
RT-GARCH | 4.1521 | 1.9775 | |||
RT-REGARCH-MIDAS | 5.5053 | 1.5423 |
注: MSE是均方误差, QLIKE是拟似然误差. MCS检验p值大于0.1 (加粗的数字)表示模型包含在MCS中, 即预测能力较好的模型. |
表8 波动率预测评价结果: 不同MIDAS滞后阶数 |
SSEC | SZSEC | ||||
MSE | QLIKE | MSE | QLIKE | ||
MIDAS滞后阶数: | |||||
GARCH | 1.0852 | 2.8992 | |||
GJR-GARCH | 1.0681 | 2.9228 | |||
EGARCH | 9.9715 | 2.8881 | |||
REGARCH | 7.8829 | 2.1432 | |||
REGARCH-MIDAS | 6.8983 | 1.9718 | |||
RT-GARCH | 8.7940 | 2.5157 | |||
RT-REGARCH-MIDAS | 6.6634 | 1.9195 | |||
MIDAS滞后阶数: | |||||
GARCH | 1.0852 | 2.8992 | |||
GJR-GARCH | 1.0681 | 2.9228 | |||
EGARCH | 9.9715 | 2.8881 | |||
REGARCH | 7.8829 | 2.1432 | |||
REGARCH-MIDAS | 6.9109 | 1.9718 | |||
RT-GARCH | 8.7940 | 2.5157 | |||
RT-REGARCH-MIDAS | 6.7212 | 1.9363 |
注: MSE是均方误差, QLIKE是拟似然误差. MCS检验p值大于0.1 (加粗的数字) 表示模型包含在MCS中, 即预测能力较好的模型. |
表9 波动率预测评价结果: 不同预测期 |
SSEC | SZSEC | ||||
MSE | QLIKE | MSE | QLIKE | ||
预测期: 5天 | |||||
GARCH | 1.3302 | 3.4610 | |||
GJR-GARCH | 1.3071 | 3.5069 | |||
EGARCH | 1.2508 | 3.5500 | |||
REGARCH | 1.2282 | 3.3653 | |||
REGARCH-MIDAS | 1.0991 | 3.3406 | |||
RT-GARCH | 1.1129 | 3.1903 | |||
RT-REGARCH-MIDAS | 1.0047 | 2.8652 | |||
预测期: 10天 | |||||
GARCH | 1.4954 | 3.7923 | |||
GJR-GARCH | 1.4745 | 3.8348 | |||
EGARCH | 1.4687 | 4.0105 | |||
REGARCH | 1.4515 | 3.7771 | |||
REGARCH-MIDAS | 1.3140 | 3.9908 | |||
RT-GARCH | 1.2434 | 3.3635 | |||
RT-REGARCH-MIDAS | 1.1855 | 3.3554 |
注: MSE是均方误差, QLIKE是拟似然误差. MCS检验p值大于0.1 (加粗的数字) 表示模型包含在MCS中, 即预测能力较好的模型. |
表10 波动率预测评价结果: 样本外R2检验 |
SSEC | SZSEC | ||||||
R2 | MSPE-adjusted | R2 | MSPE-adjusted | ||||
GJR-GARCH | 0.0157 | 2.0196 | 0.0217 | 0.9068 | |||
EGARCH | 0.0811 | 1.6205 | 0.0526 | 0.0038 | 1.0345 | 0.1504 | |
REGARCH | 0.2736 | 5.5924 | 0.0000 | 0.2607 | 6.7811 | 0.0000 | |
REGARCH-MIDAS | 0.3642 | 4.7743 | 0.0000 | 0.3199 | 7.9552 | 0.0000 | |
RT-GARCH | 0.1896 | 4.9895 | 0.0000 | 0.1323 | 5.0029 | 0.0000 | |
RT-REGARCH-MIDAS | 0.4006 | 4.7548 | 0.0000 | 0.3338 | 5.8865 | 0.0000 |
注: 表中R2是样本外R2, MSPE-adjusted是调整后的MSPE, R2 > 0说明对应模型的样本外预测能力优于基准模型. |
表11 投资组合的业绩表现 |
CER | CER | CER | ||||||
SSEC | ||||||||
GARCH | - | 0.1504 | - | 0.1165 | - | 0.1044 | ||
GJR-GARCH | 1.6125 | 0.1509 | 1.0384 | 0.1168 | 0.6922 | 0.1046 | ||
EGARCH | 21.3046 | 0.1575 | 8.0734 | 0.1192 | 5.3821 | 0.1062 | ||
REGARCH | 21.6988 | 0.1576 | 34.4875 | 0.1280 | 22.9901 | 0.1120 | ||
REGARCH-MIDAS | 91.4051 | 0.1808 | 65.5094 | 0.1383 | 43.6716 | 0.1189 | ||
RT-GARCH | 0.1227 | 10.7807 | 0.1201 | 8.1875 | 0.1071 | |||
RT-REGARCH-MIDAS | 188.0060 | 0.2130 | 111.7531 | 0.1537 | 74.5012 | 0.1292 | ||
SZSEC | ||||||||
GARCH | - | 0.3544 | - | 0.2173 | - | 0.1716 | ||
GJR-GARCH | 0.3544 | 0.2173 | -0.0016 | 0.1716 | ||||
EGARCH | 52.1986 | 0.3718 | 26.0999 | 0.2260 | 17.4003 | 0.1774 | ||
REGARCH | 160.0133 | 0.4078 | 80.0091 | 0.2440 | 53.3410 | 0.1894 | ||
REGARCH-MIDAS | 343.6988 | 0.4690 | 171.8509 | 0.2746 | 114.5682 | 0.2098 | ||
RT-GARCH | 52.3828 | 0.3719 | 28.1653 | 0.2267 | 18.7788 | 0.1778 | ||
RT-REGARCH-MIDAS | 596.5541 | 0.5532 | 272.2472 | 0.3080 | 181.5024 | 0.2321 |
注: 表中加粗且带下划线的数字表示最大数值, 加粗但不带下划线的数字表示次大数值. A是风险厌恶系数, |
柏建成, 黄云飞, 高增安, 何田, 经济政策不确定性与数字货币市场波动影响研究——基于比特币市场的实证分析[J]. 运筹与管理, 2022, 31 (5): 183- 189.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
白娟娟, 师荣蓉, 基于广义已实现测度的中国股市波动预测与VaR度量[J]. 系统科学与数学, 2021, 41 (3): 653- 666.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
蔡光辉, 徐君, 应雪海, 基于混频抽样和杠杆效应的高频波动率模型预测[J]. 系统科学与数学, 2021, 41 (7): 1985- 2005.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
高雷阜, 李伟梅, 基于Expectile和Realized GARCH模型的波动率预测[J]. 运筹与管理, 2022, 31 (2): 99- 103.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
龚旭, 曹杰, 文凤华, 杨晓光, 基于杠杆效应和结构突变的HAR族模型及其对股市波动率的预测研究[J]. 系统工程理论与实践, 2020, 40 (5): 1113- 1133.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
郭宝才, 项琳, 基于跳跃、好坏波动率的混频已实现EGARCH模型的波动率预测与风险度量[J]. 商业经济与管理, 2022, 5, 79- 97.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
黄友珀, 唐振鹏, 周熙雯, 基于偏t分布realized GARCH模型的尾部风险估计[J]. 系统工程理论与实践, 2015, 35 (9): 2200- 2208.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
蒋伟, 顾研, 基于广义已实现测度的Realized GARCH模型改进及应用[J]. 数量经济技术经济研究, 2019, 36 (7): 156- 173.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
雷立坤, 余江, 魏宇, 赖晓东, 经济政策不确定性与我国股市波动率预测研究[J]. 管理科学学报, 2018, 21 (6): 88- 98.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
李木易, 方颖, 动态混合HGARCH模型的估计和预测[J]. 管理科学学报, 2020, 23 (5): 1- 12.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
梁超, 魏宇, 马锋, 李薇, 投资者关注对中国黄金价格波动率的影响研究[J]. 系统工程理论与实践, 2022, 42 (2): 320- 332.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
刘小军, 汪寿阳, 谢海滨, 已实现波动率预测: 非对称二次滑动平均模型[J]. 计量经济学报, 2022, 2 (4): 930- 945.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
鲁万波, 亢晶浩, GAS-SKST-F模型及其在高频多元波动率预测中的应用[J]. 中国管理科学, 2022, 30 (1): 77- 87.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
王天一, 黄卓, Realized GAS-GARCH及其在VaR预测中的应用[J]. 管理科学学报, 2015, 18 (5): 79- 86.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
王天一, 刘浩, 黄卓, 基于混频数据抽样的已实现波动率长记忆模型[J]. 系统工程学报, 2018, 33 (6): 812- 822.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
吴鑫育, 侯信盟, 基于双因子已实现GARCH模型的波动率预测研究[J]. 运筹与管理, 2020, 29 (12): 207- 214.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
夏婷, 闻岳春, 经济不确定性是股市波动的因子吗?——基于GARCH-MIDAS模型的分析[J]. 中国管理科学, 2018, 26 (12): 1- 11.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
邢艳春, 廖晗, 经济政策不确定性对中国股市波动率的影响[J]. 统计与信息论坛, 2023, 38 (1): 71- 80.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
于孝建, 王秀花, 基于混频已实现GARCH模型的波动预测与VaR度量[J]. 统计研究, 2018, 35 (1): 104- 116.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
苑慧玲, 徐路, 周勇, 带有市场交易信息和随机微观噪声下的杠杆效应研究[J]. 中国管理科学, 2020, 28 (9): 12- 22.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
张一锋, 雷立坤, 魏宇, 羊群效应的新测度指数及其对我国股市波动的预测作用研究[J]. 系统工程理论与实践, 2020, 40 (11): 2810- 2824.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
郑挺国, 尚玉皇, 基于宏观基本面的股市波动度量与预测[J]. 世界经济, 2014, 37 (12): 118- 139.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
周辰月, 崔文昊, 金融资产波动率估计的最优内生抽样方案的设计与应用[J]. 计量经济学报, 2023, 3 (1): 238- 258.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
Banulescu-Radu D, Hansen P R, Huang Z, Matei M, (2018). Volatility During the Financial Crisis Through the lens of High Frequency Data: A Realized GARCH Approach[R]. Working Paper.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
Ding Z, (2016). Volatility Modeling Using GARCH: Theory and Practice[R]. Working Paper.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
Dobrev D, Szerszen P, (2010). The Information Content of High-frequency Data for Estimating Equity Return Models and Forecasting Risk[R]. Working Paper.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
Ghysels E, Santa-Clara P, Valkanov R, (2004). The MIDAS Touch: Mixed Data Sampling Regression Models[R]. Working Paper.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
Hansen P R, Huang Z, Tong C, Wang T Y, (2021). Realized GARCH, CBOE VIX, and the Volatility Risk Premium[R]. Working Paper.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_ref.label}} |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
/
〈 |
|
〉 |