I'm new to Gretl (and econometrics!) and would need help to confirm that I read the results of an augmented Dickey Fuller test correctly:

I have a series T=27

hypothesis of unit root : a=1

model : (1-L) y = b0 + b1*t + (a-1) * y(-1) + ... + e

Coeff. autocorrelation of 1st order for e : 0.044

Estimated value of (a-1) : -0.19

Test statistic : tau_ct (1) = - 1.46

p. asymptotic critic : 0.552

=> I should look at the test statistic which shows -1,46, which is negative, which means that my series can be considered as reasonably stationary and I can make an OLS regression: is this correct?

Thanks a lot for the help!

Mike

New Windows 7: Find the right PC for you. Learn more.