时间序列实验报告4

合集下载
  1. 1、下载文档前请自行甄别文档内容的完整性,平台不提供额外的编辑、内容补充、找答案等附加服务。
  2. 2、"仅部分预览"的文档,不可在线预览部分如存在完整性等问题,可反馈申请退款(可完整预览的文档不适用该条件!)。
  3. 3、如文档侵犯您的权益,请联系客服反馈,我们会尽快为您处理(人工客服工作时间:9:00-18:30)。

时间序列分析实验报告

Problem 1 : check whether the series in test1.xls is stationary or not by ADF-test ,if the series is nonstationary, then consider the nonstationarity and establish suitable model

①.create a new integer-data workfile named test1; import data series named y

②.Check series-- long-run trend----unit root test(trend stationary or unit root

process)

③.Uint root test—ADF, give your reason or how do you get your result

④.If the series y is nonstationary , please eliminate the nonstarionarity and

establish suitable model for original series , the equation should be stored in the

workfile and give name eq01

⑤.write out the equation in lag operator:

Problem2: check whether the series in test22.xls is stationary or not by ADF-test,if the series is nonstationary, then consider the nonsationarity and establish suitable model

①.create a new integer-data workfile named test22; import data series named y

②.Check series is stationary, trend stationary or unit root process by ADF-test,

give your reason or how do you get your result

③.Establish suitable model(eq01)for original series y based on your conclusion

in question 2

④.Write out the model in lag operator

实验报告结果

Problem1

In ADF test ,the trend t is under the a=0.05 in regression equation. The p value in ADF test is 0.0000

So Yt=8.991+0.01t+Xt

So Xt=0.282Xt-1 – 0.573Xt-2 + 0.797Ut-1 + Ut

Yt=8.991+0.01t+0.282Xt-1 – 0.573Xt-2 + 0.797Ut-1 + Ut Problem 2

The p value is 0.9975

The p is 0.5730

P is 0.2458

Y1=d(y)

Xt=50.95+0.886Xt-1 – 0.665Ut-1 + Ut

(1-0.886L)Xt=(1-0.665L)Ut +50.95 , Xt=d(y)

相关文档
最新文档