On Mon, 10 May 2010, Liliya Netskar wrote:
I need your help.
I would like to apply for my panel data analysis the two-step GMM
Arellano-Bond dynamic panel-data estimation, because it is more
efficient for samples with small t. Is is possible to perform it with
Gretl? The tables report results for one-step or two-step Arellano-Bond
estimation. But what are they? GMM (DIF) or GMM (SYS)?
What you get in gretl at the moment is GMM-DIF. The so-called SYS estmator
is planned and there is the chance that it shows up before long.
Riccardo (Jack) Lucchetti
Dipartimento di Economia
Università Politecnica delle Marche