GARCH模型实验 - 时间序列

更新时间:2024-05-25 14:37:01 阅读量: 综合文库 文档下载

说明:文章内容仅供预览,部分内容可能不全。下载后的文档,内容与下面显示的完全一致。下载之前请确认下面内容是否您想要的,是否完整无缺。

金融时间序列分析

探究中国A股市场收益率的波动情况

基于GARCH模型

第一部分 实验背景

自1990年12月,我国建立了上海、深圳证券交易所,20多年来,我国资本市场在拓宽融资渠道、促进资本形成、优化资源配置、分散市场风险方面发挥了不可替代的重要作用,有力推动了实体经济的发展,成为我国市场经济的重要组成部分。自1980年第一次股票发行算起,我国股票市场历经30多年,就当前的股票市场来看,股票市场的动荡和股票的突然疯涨等一系列现象和问题值得我们深入思考和深入研究。

第二部分 实验分析目的及方法

沪深300指数是在以上交所和深交所所有上市的股票中选取规模大流动性强的最具代表性的300家成分股作为编制对象,成为沪深证券所联合开发的第一个反应A股市场整体走势的指数。沪深300指数作为我国股票市场具有代表性的且作为股指期货的标的指数,以沪深300指数作为研究对象可以使得检验结果更加具有真实性和完整性,较好的反应我国股票市场的基本状况。本文在检验沪深300指数2011年1月4日到2012年12月12日的日收益率的相关时间序列特征的基础上,对序列{r}建立条件异方差模型,并研究其收益波动率。

第三部分 实验样本

3.1数据来源

数据来源于国泰安数据库。 3.2所选数据变量

沪深300指数编制目标是反映中国证券市场股票价格变动的概貌和运行状况,并能够作为投资业绩的评价标准,为指数化投资和指数衍生产品创新提供基础条件。故本文选择沪深300指数2011年1月4日到2012年12月12日的日收益率作为样本,探究中国股票市场收益率的波动情况。

第四部分 模型构建

4.1 单位根检验

观察R的图形,如下所示:

- 1 -

R6420-2-4-6-8100200300400500600700800900 图4.2 R的柱状统计图

从沪深300指数收益率序列r的线性图中,可观察到对数收益率波动的“集群”现象:波动在一些时间段内较小,在有的时间段内较大。此外,由图形可知,序列R没有截距项且没有趋势,故选择第三种形式没有截距项且不存在趋势进行单位根检验,检验结果如下:

表4.1 单位根检验结果

Null Hypothesis: R has a unit root Exogenous: None

Lag Length: 0 (Automatic - based on SIC, maxlag=21)

t-Statistic -31.29206 -2.567383 -1.941155 -1.616476

Prob.* 0.0000

Augmented Dickey-Fuller test statistic Test critical values:

1% level 5% level 10% level

*MacKinnon (1996) one-sided p-values.

单位根统计量ADF=31.29206小于临界值,且P为 0.0000,因此该序列不是单位根过程,即该序列是平稳序列。

- 2 -

200160Series: RSample 1 957Observations 957Mean Median Maximum Minimum Std. Dev. Skewness Kurtosis 0.010480-0.024000 5.049000-6.308100 1.292140 0.164917 4.8280121208040Jarque-Bera 137.5854Probability 0.000000-6-5-4-3-2-10123450

图4.2 R的正态分布检验

由图可知,沪深300指数收益率序列均值为0.010480,标准差为1.292140,偏度为0.164917,大于0,说明序列分布有长的右拖尾。峰度为4.828012,高于正态分布的峰度值3,说明收益率序列具有尖峰和厚尾的特征。JB统计量为137.5854,P值为0.00000,拒绝该对数收益率序列服从正态分布的假设。其中右偏表明总体来说,近年比较大的收益大多为正;尖峰厚尾表明有很多样本值较大幅度偏离均值,即金融市场由于利多利空消息波动较为剧烈,经常大起大落,从而有很多比较大的正收益和负收益。

4.2 检验ARCH效应

首先观察r的自相关图,其结果如下:

Date: 12/16/14 Time: 08:16 Sample: 1 957

Included observations: 957

Autocorrelation | | | | | | | | | | | | | | | | | | | | | | | |

Partial Correlation | | | | | | | | | | | | | | | | | | | | | | | |

AC PAC Q-Stat Prob 1 -0.011 -0.011 2 0.034

0.034

3 -0.004 -0.004 4 -0.006 -0.008 5 0.029 7 0.064 8 0.013 9 0.027 10 0.052 11 0.017

0.029 0.061 0.017 0.023 0.052 0.019

6 -0.039 -0.038

0.1244 1.2510 1.2703 1.3082 2.1091 3.6035 7.5711 7.7248 8.4167 11.073 11.343 13.327

0.724 0.535 0.736 0.860 0.834 0.730 0.372 0.461 0.493 0.352 0.415 0.346

12 -0.045 -0.053

- 3 -

| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | *| | | | | | | | | | | | | |

| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |

13 -0.033 -0.031 14 0.035 15 0.006 17 0.008 18 0.039

0.035 0.005 0.005 0.034

14.405 15.630 15.661 15.723 15.792 17.274 17.281 18.112 18.518 18.652 21.077 21.096 21.205 21.446 23.764 26.255 26.886 31.145 31.170 33.848 34.007 36.401 37.024 37.160

0.346 0.336 0.405 0.472 0.539 0.504 0.571 0.580 0.616 0.667 0.576 0.633 0.681 0.719 0.643 0.559 0.578 0.408 0.458 0.378 0.419 0.358 0.376 0.415

16 -0.008 -0.012

19 -0.003 -0.004 20 -0.029 -0.028 21 -0.020 -0.022 22 0.012

0.018

23 -0.050 -0.046 24 0.004 -0.001 25 0.011 27 0.048 28 0.050

0.006 0.050 0.055

26 -0.016 -0.015

29 -0.025 -0.033 30 -0.066 -0.057 31 -0.005 33 0.013

0.004 0.013

32 -0.052 -0.058 34 -0.049 -0.042 35 -0.025 -0.037 36 0.012

0.006

图4.3 R的自相关图

由自相关图可知,该序列不存在自相关性。因此对R进行常数回归。其回归结果如下:

表4.2 回归结果

Dependent Variable: R Method: Least Squares Date: 12/16/14 Time: 08:10 Sample: 1 957

Included observations: 957

Variable C

R-squared Adjusted R-squared S.E. of regression Sum squared resid Log likelihood

Coefficient 0.010480

Std. Error 0.041769

t-Statistic 0.250905

Prob. 0.8019 0.010480 1.292140 3.351521 3.356603 3.353457

0.000000 Mean dependent var 0.000000 S.D. dependent var 1.292140 Akaike info criterion 1596.162 Schwarz criterion -1602.703 Hannan-Quinn criter.

- 4 -

Durbin-Watson stat

2.020315

由上表可知,对常数的回归结果并不显著。下面得到残差平方的自相关图:

Date: 12/16/14 Time: 08:18 Sample: 1 957

Included observations: 957

Autocorrelation | | |* | | | | | | | | | |* | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |

Partial Correlation | | |* | | | | | | | | | |* | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |

AC PAC Q-Stat Prob 1 0.050 2 0.107 3 0.020 4 0.035 5 0.020 6 0.031 7 0.084 8 0.015 9 0.045 10 0.061 12 0.039 13 0.053

0.050 0.105 0.010 0.023 0.014 0.024 0.078 0.001 0.027 0.054 0.025 0.044

2.3771 13.380 13.769 14.958 15.331 16.271 23.070 23.278 25.212 28.818 28.999 30.492 33.261 33.268 33.269 33.278 33.657 35.450 35.490 36.486 39.334 39.829 40.012 42.216 42.322 42.585 43.014 43.642 44.979 45.797 46.343 47.339 48.765 49.134 49.734

0.123 0.001 0.003 0.005 0.009 0.012 0.002 0.003 0.003 0.001 0.002 0.002 0.002 0.003 0.004 0.007 0.009 0.008 0.012 0.013 0.009 0.011 0.015 0.012 0.017 0.021 0.026 0.030 0.030 0.032 0.038 0.040 0.038 0.045 0.051

11 0.014 -0.003

14 0.003 -0.018 15 -0.001 -0.014 16 -0.003 -0.011 17 0.020 18 0.043 20 0.032 21 0.054 23 0.014 25 0.010

0.010 0.041 0.014 0.052 0.001 0.003

19 0.006 -0.010

22 -0.022 -0.039 24 -0.047 -0.048 26 -0.016 -0.009 27 -0.021 -0.030 28 0.025 30 0.029 31 0.023 32 0.032 34 0.019 35 0.025

0.023 0.019 0.031 0.027 0.022 0.030 - 5 -

29 -0.037 -0.031

33 -0.038 -0.045

| |

| |

36 0.016

0.018

49.984

0.061

图4.4 残差平方的自相关图

由上图可知,残差平方序列在滞后三阶并不异于零,即存在自相关性,进一步进行lm检验,这里选取滞后将阶数为3,检验结果如下:

表4.3 ARCH效应检验结果

Heteroskedasticity Test: ARCH F-statistic

4.373176 Prob. F(3,950)

0.0046 0.0046

Obs*R-squared

12.99530 Prob. Chi-Square(3)

由上表可知,p值为0.0046,因此在1%的显著水平下是存在ARCH效应的。选择滞后阶数更高的进行检

验,发现滞后4阶也满足在1%的显著水平下存在ARCH效应,再选取其他高阶进行检验,发现高阶残差平方项均不满足。

4.3 模型的估计

分别估计ARCH(2)、ARCH(1)和GARCH(1,1),由于R不存在自相关性,而且对常数回归也不显著,因此不对均值方程进行设定,之设定方差方程。AECH(2)估计结果如下:

表4.4 arch(2)模型的估计结果

Dependent Variable: R

Method: ML - ARCH (Marquardt) - Normal distribution Date: 12/16/14 Time: 08:38 Sample: 1 957

Included observations: 957

Convergence achieved after 8 iterations Presample variance: backcast (parameter = 0.7) GARCH = C(1) + C(2)*RESID(-1)^2 + C(3)*RESID(-2)^2

Variable

C RESID(-1)^2 RESID(-2)^2 R-squared Adjusted R-squared S.E. of regression Sum squared resid Log likelihood Durbin-Watson stat

Coefficient

Std. Error

z-Statistic 18.41652 2.219053 4.432849

Prob. 0.0000 0.0265 0.0000 0.010480 1.292140 3.336256 3.351503 3.342063 - 6 -

Variance Equation 1.409961 0.047531 0.106284

0.076560 0.021420 0.023977

-0.000066 Mean dependent var 0.000979 S.D. dependent var 1.291507 Akaike info criterion 1596.268 Schwarz criterion -1593.399 Hannan-Quinn criter. 2.020182

可以看出,残差平方滞后项的系数在5%的显著水平下都显著,因此选择

arch(2)合适,再选择

ARCH(1)。

表4.5 arch(1)模型的估计结果

Dependent Variable: R

Method: ML - ARCH (Marquardt) - Normal distribution Date: 12/16/14 Time: 08:40 Sample: 1 957

Included observations: 957

Convergence achieved after 7 iterations Presample variance: backcast (parameter = 0.7) GARCH = C(1) + C(2)*RESID(-1)^2

Variable

C RESID(-1)^2 R-squared Adjusted R-squared S.E. of regression Sum squared resid Log likelihood Durbin-Watson stat

Coefficient

Std. Error

z-Statistic 25.50884 2.090131

Prob. 0.0000 0.0366 0.010480 1.292140 3.350173 3.360337 3.354044

Variance Equation 1.594810 0.043267

0.062520 0.020701

-0.000066 Mean dependent var 0.000979 S.D. dependent var 1.291507 Akaike info criterion 1596.268 Schwarz criterion -1601.058 Hannan-Quinn criter. 2.020182

可以看出,残差平方滞后项的系数在5%的显著水平下显著,因此选择ARCH(1)合适。下面对

GARCH(1,1)进行估计。

表4.6 GARCH(1,1)模型的估计结果

Dependent Variable: R

Method: ML - ARCH (Marquardt) - Normal distribution Date: 12/16/14 Time: 08:42 Sample: 1 957

Included observations: 957

Convergence achieved after 9 iterations Presample variance: backcast (parameter = 0.7) GARCH = C(1) + C(2)*RESID(-1)^2 + C(3)*GARCH(-1)

Variable

C

Coefficient

Std. Error

z-Statistic 2.073026 - 7 -

Prob. 0.0382

Variance Equation 0.046373

0.022370

RESID(-1)^2 GARCH(-1)

R-squared Adjusted R-squared S.E. of regression Sum squared resid Log likelihood Durbin-Watson stat

0.038396 0.934896

0.009194 0.019410

4.176296 48.16515

0.0000 0.0000 0.010480 1.292140 3.326751 3.341998 3.332558

-0.000066 Mean dependent var 0.000979 S.D. dependent var 1.291507 Akaike info criterion 1596.268 Schwarz criterion -1588.850 Hannan-Quinn criter. 2.020182

以上模型的系数均满足非负性,而且在5%的水平下显著。 4.4模型残差的检验

下面进行残差的自相关性的检验,检验结果如下:

Date: 12/16/14 Time: 08:50 Sample: 1 957

Included observations: 957

Autocorrelation | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |

Partial Correlation | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |

AC PAC Q-Stat Prob 1 0.002 2 0.020

0.002 0.020

0.0042 0.3950 0.4260 0.5415 1.1481 3.5743 7.2970 7.3261 7.7988 10.192 10.313 11.926 13.305 14.761 14.832

0.949 0.821 0.935 0.969 0.950 0.734 0.399 0.502 0.555 0.424 0.502 0.452 0.425 0.395 0.464

3 -0.006 -0.006 4 -0.011 -0.011 5 0.025 7 0.062 8 0.005 9 0.022 10 0.050 11 0.011

0.025 0.061 0.007 0.020 0.049 0.014

6 -0.050 -0.050

12 -0.041 -0.048 13 -0.038 -0.031 14 0.039 15 0.009

0.038 0.008

图4.5 ARCH(2)模型残差项的自相关图

Date: 12/16/14 Time: 08:51 Sample: 1 957

Included observations: 957

Autocorrelation

Partial Correlation

AC PAC Q-Stat Prob

- 8 -

| | | | | | | | | | | | | | | | | | | | | | | | | | | | | |

| | | | | | | | | | | | | | | | | | | | | | | | | | | | | |

1 -0.004 -0.004 2 0.032

0.032

3 -0.005 -0.005 4 -0.007 -0.009 5 0.028 7 0.066 8 0.012 9 0.029 10 0.055 11 0.015

0.029 0.064 0.015 0.025 0.054 0.017

6 -0.039 -0.039

0.0190 1.0108 1.0351 1.0887 1.8669 3.3497 7.5614 7.7017 8.5082 11.480 11.699 13.620 14.860 16.013 16.040

0.890 0.603 0.793 0.896 0.867 0.764 0.373 0.463 0.484 0.321 0.387 0.326 0.316 0.313 0.379

12 -0.044 -0.053 13 -0.036 -0.032 14 0.034 15 0.005

0.034 0.005

图4.6 ARCH(1)模型残差项的自相关图

Date: 12/16/14 Time: 08:52 Sample: 1 957

Included observations: 957

Autocorrelation | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |

Partial Correlation | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |

AC PAC Q-Stat Prob 1 0.010 2 0.036

0.010 0.036

0.0894 1.3190 1.3196 1.3196 2.2129 3.8917 7.3928 7.4137 8.0945 11.607 11.786 13.630 14.693 16.088 16.100

0.765 0.517 0.724 0.858 0.819 0.691 0.389 0.493 0.525 0.312 0.380 0.325 0.327 0.308 0.375

3 -0.001 -0.001 4 -0.000 -0.001 5 0.030 7 0.060 8 0.005 9 0.027 10 0.060 11 0.014

0.031 0.059 0.006 0.022 0.059 0.013

6 -0.042 -0.042

12 -0.044 -0.054 13 -0.033 -0.028 14 0.038 15 0.004

0.038 0.003

图4.7 GARCH(1,1)模型残差项的自相关图

观察残差的自相关图,可以看出均不存在自相关性。下面观察残差平方的自相关图。

Date: 12/16/14 Time: 08:53

- 9 -

Sample: 1 957

Included observations: 957

Autocorrelation | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |

Partial Correlation | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |

AC PAC Q-Stat Prob -0.023 -0.023 1

2 -0.001 -0.002 3 -0.002 -0.002 4 0.002 5 0.001 6 0.025 7 0.070 8 0.001 9 0.055 10 0.069 11 0.007 12 0.025 13 0.030 14 0.007

0.002 0.001 0.025 0.071 0.004 0.056 0.073 0.011 0.026 0.029 0.004

0.5267 0.5279 0.5304 0.5333 0.5336 1.1177 5.8808 5.8815 8.8505 13.489 13.533 14.122 14.992 15.039 15.062

0.468 0.768 0.912 0.970 0.991 0.981 0.554 0.660 0.451 0.198 0.260 0.293 0.308 0.376 0.447

15 -0.005 -0.007

图4.8 ARCH(2)模型残差平方的自相关图

Date: 12/16/14 Time: 08:54 Sample: 1 957

Included observations: 957

Autocorrelation | | |* | | | | | | | | | |* | | | | | | | | | | | | | | | | |

Partial Correlation | | |* | | | | | | | | | |* | | | | | | | | | | | | | | | | |

AC PAC Q-Stat Prob 1 -0.000 -0.000 2 0.109 3 0.001 4 0.027 5 0.005 6 0.028 7 0.087 8 0.010 9 0.043 10 0.063 12 0.040 13 0.047

0.109 0.001 0.015 0.005 0.023 0.087 0.005 0.025 0.062 0.026 0.043

0.0002 11.411 11.413 12.101 12.126 12.862 20.108 20.212 21.998 25.905 25.929 27.454 29.603 29.617 29.645

0.990 0.003 0.010 0.017 0.033 0.045 0.005 0.010 0.009 0.004 0.007 0.007 0.005 0.009 0.013

11 0.005 -0.005

14 0.004 -0.013 15 -0.005 -0.017

- 10 -

图4.9 ARCH(1)模型残差平方的自相关图

Date: 12/16/14 Time: 08:55 Sample: 1 957

Included observations: 957

Autocorrelation | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |

Partial Correlation | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |

AC PAC Q-Stat Prob 1 -0.031 -0.031 2 0.045

0.044

3 -0.029 -0.027 4 -0.024 -0.027 5 -0.017 -0.016 6 -0.002 -0.001 7 0.065 9 0.050 10 0.051

0.065 0.043 0.059

8 -0.013 -0.011

0.9430 2.8653 3.6894 4.2329 4.5182 4.5219 8.5997 8.7598 11.144 13.696 14.097 14.103 14.358 14.393 15.226

0.332 0.239 0.297 0.375 0.477 0.606 0.283 0.363 0.266 0.187 0.228 0.294 0.349 0.421 0.435

11 -0.020 -0.019 12 -0.002 -0.004 13 0.016

0.023

14 -0.006 -0.006 15 -0.029 -0.029

图4.10 GARCH(1,1)模型残差平方的自相关图

ARCH(2)模型和GARCH(1,1)模型残差平方序列不存在自相关性,而ARCH(1)模型残差平方序列存在自相关性,故ARCH(1)模型不适合。下面进行正态性检验。

140120100806040200-4-3-2-101234Series: Standardized ResidualsSample 1 957Observations 957Mean Median Maximum Minimum Std. Dev. Skewness Kurtosis Jarque-BeraProbability 0.000873-0.019032 4.141549-3.934093 1.000522 0.183238 4.317777 74.59976 0.000000 图4.11 ARCH(2)模型的柱形统计图

- 11 -

140120100806040200-4-3-2-101234Series: Standardized ResidualsSample 1 957Observations 957Mean Median Maximum Minimum Std. Dev. Skewness Kurtosis Jarque-BeraProbability 0.002827-0.021716 4.097276-4.558566 1.002241 0.137876 4.454455 87.38517 0.000000 图4.12 GARCH(1,1)模型柱形统计图

由以上结果可知,均不满足正态分布。再进行ARCH效应的检验。

表4.7 ARCH(1)模型残差ARCH效应检验

Heteroskedasticity Test: ARCH F-statistic

0.173845 Prob. F(3,950)

0.9141 0.9137

Obs*R-squared

0.523445 Prob. Chi-Square(3)

表4.8 GARCH(1,1)模型残差ARCH效应检验

Heteroskedasticity Test: ARCH F-statistic

1.154565 Prob. F(3,950)

0.3261 0.3252

Obs*R-squared

3.465643 Prob. Chi-Square(3)

LM检验的P值均大于5%,故不存在ARCH效应。下面对三个模型进行比较。

表4.9 不同模型结果对比

AIC SC 残差检验 ARCH(2) 3.336256 3.351503 ARCH(1) 3.350173 3.360337 GARCH(1,1) 3.326751 3.341998 无自相关性,无ARCH效应,不满足正态性 存在自相关性,无ARCH效应,不满足正态性 无自相关性,无ARCH效应,不满足正态性 由上表对比结果可知,GARCH(1,1)效果最好,故在此选择GARCH(1,1)模型。

4.5 不同GARCH模型的对比分析

- 12 -

尝试建立不同的GARCH模型形式,TARCH模型、EGARCH模型、ARCH-M模型。

表4.10 TARCH模型的估计结果

Dependent Variable: R

Method: ML - ARCH (Marquardt) - Normal distribution Date: 12/16/14 Time: 22:15 Sample: 1 957

Included observations: 957

Convergence achieved after 11 iterations Presample variance: backcast (parameter = 0.7)

GARCH = C(1) + C(2)*RESID(-1)^2 + C(3)*RESID(-1)^2*(RESID(-1)<0) + C(4)*GARCH(-1)

Variable

C RESID(-1)^2

RESID(-1)^2*(RESID(-1)<0)

GARCH(-1)

R-squared

Coefficient

Std. Error

z-Statistic 2.124299 3.899567 1.278813 44.86304

Prob. 0.0336 0.0001 0.2010 0.0000 0.010480 1.292140 3.328008 3.348338 3.335751

Variance Equation 0.051813 0.035207 0.014738 0.927946

0.024391 0.009028 0.011525 0.020684

-0.000066 Mean dependent var 0.000979 S.D. dependent var 1.291507 Akaike info criterion 1596.268 Schwarz criterion -1588.452 Hannan-Quinn criter. 2.020182

Adjusted R-squared S.E. of regression Sum squared resid Log likelihood Durbin-Watson stat

由γ系数不显著 ,因此不能利用非对称模型对样本数据进行估计。

表4.11 EGARCH模型的估计结果

Dependent Variable: R

Method: ML - ARCH (Marquardt) - Normal distribution Date: 12/16/14 Time: 22:18 Sample: 1 957

Included observations: 957

Convergence achieved after 12 iterations Presample variance: backcast (parameter = 0.7)

LOG(GARCH) = C(1) + C(2)*ABS(RESID(-1)/@SQRT(GARCH(-1))) + C(3) *RESID(-1)/@SQRT(GARCH(-1)) + C(4)*LOG(GARCH(-1))

Variable

Coefficient

Std. Error

z-Statistic - 13 -

Prob.

Variance Equation C(1) C(2) C(3) C(4)

R-squared Adjusted R-squared S.E. of regression Sum squared resid Log likelihood Durbin-Watson stat

-0.063973 0.109035 -0.014034 0.967261

0.015847 0.022411 0.010169 0.016573

-4.036994 4.865277 -1.379975 58.36433

0.0001 0.0000 0.1676 0.0000 0.010480 1.292140 3.328490 3.348819 3.336233

-0.000066 Mean dependent var 0.000979 S.D. dependent var 1.291507 Akaike info criterion 1596.268 Schwarz criterion -1588.682 Hannan-Quinn criter. 2.020182

由γ系数C(3)不显著,因此不能利用非对称模型对样本数据进行估计。

表4.12 ARCH-M模型的估计结果

Dependent Variable: R

Method: ML - ARCH (Marquardt) - Normal distribution Date: 12/16/14 Time: 22:31 Sample: 1 957

Included observations: 957

Convergence achieved after 10 iterations Presample variance: backcast (parameter = 0.7) GARCH = C(2) + C(3)*RESID(-1)^2 + C(4)*GARCH(-1)

Variable @SQRT(GARCH)

C RESID(-1)^2 GARCH(-1)

R-squared Adjusted R-squared S.E. of regression Sum squared resid Log likelihood Durbin-Watson stat

Coefficient 0.009831

Std. Error 0.032322

z-Statistic 0.304144 2.065507 4.182745 48.14421

Prob. 0.7610 0.0389 0.0000 0.0000 0.010480 1.292140 3.328742 3.349072 3.336485

Variance Equation 0.046265 0.038536 0.934829

0.022399 0.009213 0.019417

0.000115 Mean dependent var 0.000115 S.D. dependent var 1.292066 Akaike info criterion 1595.978 Schwarz criterion -1588.803 Hannan-Quinn criter. 2.020552

均指项不显著,因此不考虑ARCH-M模型,也不考虑该模型与推广其他GARCH模型的结合形式。综上可知,GARCH(1,1)效果最好,故在此选择GARCH(1,1)模型。这也说明沪深300指数的收益率影

- 14 -

响中不存在非对称性。 4.6 模型的预测

选择GARCH(1,1)模型进行预测,预测结果如下。

3210-1-2-3930Forecast: RF1Actual: RForecast sample: 930 960Included observations: 28Root Mean Squared Error Mean Absolute Error Mean Abs. Percent Error Theil Inequality Coefficient Bias Proportion Variance Proportion Covariance Proportion 935940RF1945950?2 S.E.9559602.0610611.503282100.00001.0000000.180765NANA1.551.501.451.401.351.301.251.20930935940945950955960Forecast of Variance

图4.13 GARCH(1,1)模型

预测值为0,而且预测协方差误与方差误没有显示。

- 15 -

响中不存在非对称性。 4.6 模型的预测

选择GARCH(1,1)模型进行预测,预测结果如下。

3210-1-2-3930Forecast: RF1Actual: RForecast sample: 930 960Included observations: 28Root Mean Squared Error Mean Absolute Error Mean Abs. Percent Error Theil Inequality Coefficient Bias Proportion Variance Proportion Covariance Proportion 935940RF1945950?2 S.E.9559602.0610611.503282100.00001.0000000.180765NANA1.551.501.451.401.351.301.251.20930935940945950955960Forecast of Variance

图4.13 GARCH(1,1)模型

预测值为0,而且预测协方差误与方差误没有显示。

- 15 -

本文来源:https://www.bwwdw.com/article/ada7.html

Top