2
$\begingroup$

I am trying to determine if I should include an "intercept" or a "trend and intercept" when using the Augmented Dickey-Fuller (ADF) test. I ran a regression with my dependent variable and a time trend and both the intercept and trend were statistically significant. Is this statistical significance what determines if I should include a "trend and intercept" in the ADF test? My data is unstructured/undated. The series contains 252 observations and there are about 6 observations per year from 1970-2014. Below are my regression results and a graph of the raw data.

enter image description here

enter image description here

Improve this question
$\endgroup$
1
  • $\begingroup$ Have you checked out existing posts on Dickey-Fuller test? See, for example, here and here. $\endgroup$
    – Richard Hardy
    Commented Mar 3, 2015 at 7:21

1 Answer 1

Reset to default
-1
$\begingroup$ 
library(tseries)
library(urca)
data2<-na.remove(data1$SANDP) #assumed one dataset
    data2
    c<-adf.test(data2,k=2)
    c
    summary(c$statistic)

useful command for you

summary(ur.df(data2,type=c("drift"),lags=2,selectlags =c("Fixed")))
Improve this answer
$\endgroup$
1
  • $\begingroup$ you can change type=drift /none/trend. $\endgroup$
    – Harshil Gandhi
    Commented Jan 29, 2016 at 6:47

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.