[Gretl-users] Dickey Fuller

Hi I observe a strange thin running Dickey Fuller tests: It's irrelevant if I run this test on an expected stationary or non-stationary time series. The result of the p-valu i always 0,5!!! Anybody else has observed this? Is it possible to solve this? By the way: it's a new nice feature that the AR / MA lags of the Dickey Fuller Test are now possible with more than 4, but it's not possible to set an lag order higher than 4 in the ARMA model - WHY? I'm running version 1.3.0 und Linux and also the windows version. And: Where have the model selection criteria infos gone? In previous versions, there where the Standard-Criterias like AIK, R-squared and so on also in the Dickey Fuller Test-Output. Robert