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

On Fri, 1 Jan 2016, oleg_komashko(a)ukr.net wrote: > I think it's a good idea You can download it at > http://ricardo.ecn.wfu.edu/gretl/staging_fnfiles/lagreg.zip I'm not > sure, it seems less general but more easy to use It's intended mostly > for intermediate level courses Also I almost finished functions for > automated mean and median lags computing

> 1 січня 2016, 13:39:01, від "Artur Tarassow" < > artur.tarassow(a)googlemail.com >: > > Actually the dynMultipl-Package needs some revision. I already started > to update the package and hopefully will upload it soon. 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