Augmented Dickey–Fuller test

[kiki12]

What is the difference in the output of the unit root test between "Pr < Rho" and "Pr < Tau"? How should I interpret them?

[Ksharp]

Since it is about SAS/ETS, better post your question at Forecasting Forum:
https://communities.sas.com/t5/SAS-Forecasting-and-Econometrics/bd-p/forecasting_econometrics

And If I was right, "Pr < Rho" is for parameter method, but "Pr < Tau" is for non-parameter method.

[Rick_SAS]

See the documentation at https://go.documentation.sas.com/doc/en/pgmsascdc/9.4_3.5/etsug/etsug_macros_sect019.htm 

It explains that there are two test statistics:

• the regression-coefficient-based test statistic. The test statistic is Rho and the test is called the Rho test.
• the studentized test statistic, which is called the Tau test.

The doc also shows the asymptotic distributions of these test statistics under the null hypothesis.