On Sun, 25 Jan 2015, Jan Tille wrote: > Dear users, > > I have a short question regarding the estimation of a logit model, when > data is in panel format. Does Gretl automatically conduct a fixed > effects estimation? I ask because for probit models, there is a random > effects option. > > Thanks in advance,
No, if you just run "logit" on a panel dataset you get the pooled estimator. Howevere, there is a "felogit" function package which gives you the FE estimator. ------------------------------------------------------- Riccardo (Jack) Lucchetti Dipartimento di Scienze Economiche e Sociali (DiSES) Università Politecnica delle Marche (formerly known as Università di Ancona) r.lucchetti(a)univpm.it http://www2.econ.univpm.it/servizi/hpp/lucchetti -------------------------------------------------------
