0
$\begingroup$

I need to check several interest rate time series for stationarity with ADF test, lag = 2.

SAS output generates three types of test statistics: Rho, Tau and F. for three types of test (Trend, Single Mean and Zero Mean). I would like to ask several questions because they show different results in my case.

  1. Does someone know, how should I choose which type of test to use, Trend, Single Mean or Zero Mean? Looking at graphs, my time series do not have strong trend, but there are some periods with trend.
  2. And more important one, what is the difference between Rho and Tau statistics? What to do if they contradict?
  3. What is to be used for Single mean type ADF with lag 2? and what if Trend type?

P.S. This paper was supposed to explain the difference (Dickey, D. A. (2005). “Stationarity Issues in Time Series Models.” ). So, as I understand it, Rho is normalized bias test.

Improve this question
$\endgroup$
1
  • $\begingroup$ Please clarify your specific problem or provide additional details to highlight exactly what you need. As it's currently written, it's hard to tell exactly what you're asking. $\endgroup$
    – Community Bot
    Commented Nov 30 at 22:53

0

Reset to default

Your Answer

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