求教，单位根检验通过，但是自相关性全部显著，怎么建立GARCH模型啊，求大神指教

3318

收藏 2016-04-14

这个是序列的单位根检验结果：

t-Statistic    Prob.*

Augmented Dickey-Fuller test statistic -35.34578    0.0000
Test critical values: 1% level -3.434639
5% level -2.863322
10% level -2.567767

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

Augmented Dickey-Fuller Test Equation
Dependent Variable: D(RH)
Method: Least Squares
Date: 04/14/16 Time: 15:15
Sample (adjusted): 3 1456
Included observations: 1454 after adjustments

Variable Coefficient Std. Error t-Statistic Prob.

RH(-1) -0.924900 0.026167 -35.34578 0.0000
C 4.69E-05 0.000389 0.120534 0.9041

R-squared 0.462486       Mean dependent var -1.46E-05
Adjusted R-squared 0.462116       S.D. dependent var 0.020211
S.E. of regression 0.014823       Akaike info criterion -5.583878
Sum squared resid 0.319042       Schwarz criterion -5.576613
Log likelihood 4061.480       Hannan-Quinn criter. -5.581167
F-statistic 1249.324       Durbin-Watson stat 1.988308
Prob(F-statistic) 0.000000

显示是平稳的，但是自相关序列图，原谅我看不懂它到底是个什么情况
Date: 04/14/16 Time: 15:22
Sample: 1 1500
Included observations: 1455

Autocorrelation Partial Correlation AC    PAC    Q-Stat    Prob

      |*    |          |*    | 1 0.075 0.075 8.2185 0.004
      |    |          *|    | 2 -0.063 -0.069 14.063 0.001
      |    |          |    | 3 0.009 0.020 14.188 0.003
      |    |          |    | 4 0.070 0.064 21.444 0.000
      |    |          |    | 5 0.029 0.021 22.702 0.000
   *|    |          |    | 6 -0.068 -0.064 29.479 0.000
      |    |          |    | 7 0.040 0.053 31.769 0.000
      |    |          |    | 8 0.066 0.047 38.231 0.000
      |    |          |    | 9 0.006 0.001 38.292 0.000
      |    |          |    | 10 -0.046 -0.034 41.461 0.000
      |    |          |    | 11 -0.050 -0.047 45.107 0.000
      |    |          |    | 12 0.033 0.023 46.690 0.000
      |    |          |    | 13 0.051 0.045 50.439 0.000
      |    |          |    | 14 -0.033 -0.027 52.017 0.000
      |    |          |    | 15 -0.000 0.013 52.017 0.000
      |    |          |    | 16 0.059 0.046 57.121 0.000
      |    |          |    | 17 0.022 0.006 57.860 0.000
      |    |          |    | 18 -0.001 0.016 57.861 0.000
      |    |          |    | 19 -0.004 0.006 57.881 0.000
      |    |          |    | 20 0.056 0.040 62.557 0.000
      |    |          |    | 21 0.067 0.051 69.098 0.000
      |    |          |    | 22 -0.023 -0.021 69.853 0.000
   *|    |          *|    | 23 -0.112 -0.106 88.448 0.000
      |    |          |    | 24 -0.020 -0.016 89.013 0.000

这样没有办法确定均值方程啊，一阶二阶差分也全部都是显著的。