Am 12.03.2008 16:18, scottd.orr at comcast.net schrieb: > The manual seems to suggest that gretl's normal procedure for handling > of lags makes the Arrellano/Bond estimator unnecessary--but it doesn't > give any detail on that procedure. Or am I missing something? > didn't that refer to the Anderson/Hsiao estimator? They are not the same. -sven