郭同学2019-06-06 10:16:14
Q. The most appropriate conclusion that follows from the result of the Engle–Granger test is that the two time series are: cointegrated and tests of the estimates of the intercept and slope are thus valid. not cointegrated and tests of the estimates of the intercept and slope are thus valid. cointegrated and tests of the estimates of the intercept and slope are thus not valid. 题干相关见附件,这道题麻烦老师讲解下,没有思路。 条件error term has a unit root说明了啥啊?。。。
回答(1)
Chris Lan2019-06-06 10:57:06
同学你好,我觉得这个题应该是选A选项,他说时间序列数据有单位根,说明协方差不平稳,这个时间要建模,就必须要协整,因此需要通过DFEG检验,证明两组数据是协整的,之后还要看回归方程的截距和斜率是否显著,否则方程也没有意义。
- 评论(0)
- 追问(6)
- 追问
-
但是题目说Dickey–Fuller test rejects the null hypothesis ,是df检验拒绝的啊,没有单位根,然后又说rror term has a unit root
- 追答
-
同学你好,that后面是对前面的修饰,是说他reject的原假设就是有单位根,DF检验的H0是g=0,g=b1-1,如果等于0就说明b1=1,就是有单位根啊。
- 追问
-
reject g=0,说明的是没有单位根啊,拒绝了啊,这个和我表达的DF检验拒绝了不是一样的么?。。。
- 追答
-
同学你好,这个逻辑是对的,这段是原版文原文。
If the (Engle–Granger) Dickey–Fuller test fails to reject the null hypothesis that the error term has a unit root, then we conclude that the error term in the regression is not covariance stationary. Therefore, the two time series are not cointegrated. In this case any regression relation between the two series is spurious.
我帮你总结一下:
DFEG TEST
fail to reject H0 (error term has a unit root) ,then conclude error term is not covariance stationary, therefore not cointegrated.
otherwise, reject H0 ,then conclude error term is covariance stationary ,therefore cointegrated.
- 追问
-
我就是看了原版的原文没看懂,就像我最开始问的,条件error term has a unit root说明了啥不太明白,这个和DFtest本身H0的判断组合起来怎么看的没太懂。。。
- 追答
-
同学你好,
EG test:用于检验是否出现协整,例如,有两组时间序列数据xt和yt,首先使用DF-test,验证发现两组时间序列都有unit root问题。此时做一个线性回归,回归方程为yt=b0+b1xt+εt,进行EG-test(Engle–Granger test)
H0:b1=0,即error term has a unit root,也意味着no cointegration
Ha:b1≠0,也意味着cointegration
如果可以拒绝原假设,说明xt这组时间序列数据可以用来解释yt这组时间序列数据,虽然两组时间序列数据都是协方差不平稳的,但是他们是有线性关系存在的,因此它们就是协整的可建模的


评论
0/1000
追答
0/1000
+上传图片