Re: [Gretl-users] Open... to Artur

Dear Riccardo, Thank you! I really neglected filter() up to the moment! Dear Artur, After Riccardo's note we are simply bounded to make something  interesting. Oleh P.S. May I make use this opportunity and ask Riccardo a somewhat silly question: With the file you sent me I failed to reproduce Table 17.8 in Greene, 7-th, case Logit F.E.(C)^b, using felogit It should be the same Chamberlain’s estimator.  2 січня 2016, 18:49:59, від "Riccardo (Jack) Lucchetti" < r.lucchetti(a)univpm.it >: On Fri, 1 Jan 2016, oleg_komashko(a)ukr.net wrote: None of my business, really, but if you two guys could cooperate for putting together a nice package for ARDL/ECM, that would be _very_ nice. By the way: I've noticed that people tend to overlook the filter() function, which can do amazing things for you ;-) <hansl> open AWM --quiet series y = ln(YER) series c = ln(PCR) series w = ln(WLN/PCD) ols c const time y(0 to -4) w(0 to -2) c(-1 to -2) ycoef = $coeff[3:7] wcoef = $coeff[8:10] ARcoef = $coeff[11:12] scalar horizon = 20 matrix shock = ones(horizon + 1, 2) shock[2:,1] = 0 multy = filter(shock, ycoef, ARcoef) multw = filter(shock, wcoef, ARcoef) sim_y = quantile(filter(1 | mnormal(horizon, 1000), ycoef, ARcoef)', 0.5)' print multy multw sim_y </hansl> I'm sure you two guys need no pedantic explanation of the above ------------------------------------------------------- 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 ------------------------------------------------------- _______________________________________________ Gretl-users mailing list Gretl-users(a)lists.wfu.edu http://lists.wfu.edu/mailman/listinfo/gretl-users