garchfit significance

Question

Yoshiko Kawashima 2011-11-16

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/21395-garchfit-significance

what is the exact level of t-stat in the garchfit outcome to become significance for 1% and 5%

    Parameter      Value        Error       T Statistic 
 -----------   -----------   ------------   -----------
           C    -0.0013526     0.0013368       -1.0119
           K    0.00027647     0.00014944       1.8500
    GARCH(1)    0.77871        0.10106          7.7057
     ARCH(1)    0.073557       0.028595         2.572

0 个评论
显示 -2更早的评论隐藏 -2更早的评论

请先登录，再进行评论。

请先登录，再回答此问题。

Answer 1

Wayne King 2011-11-16

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/21395-garchfit-significance#answer_28175

在 MATLAB Online 中打开

You can evaluate that statistic on the t(N-p) pdf where N is the length of the time series and p is the number of parameters you are estimating. Keep in mind that for even small time series lengths, this N-p number will exceed 30. If you have a t distribution where the number of degrees of freedom exceeds 30, then you can essentially use the N(0,1) distribtuion.

Compare:

1-tcdf(2,30)

ans =

0.0273

1-normcdf(2,0,1)

ans =

0.0228

So for your T statistic of 1.85, take your time series length - the number of parameters you are estimating and set that equal to dof, then do:

2*(1-tcdf(1.85,dof))

that gives you the significance level.