[Gretl-users] AR(3) calculation

First of all thank to all of you Sven, Riccardo and Ignacio I could fix the problem. Would it be possible to create a database with scripts so that people can have access to fixed scripts which would be of great help for beginners. Please find below the output of my simulation. It is not clear to me why I get U = 0 for the first three observations (1-3). Below the script you'll find my calculations done manually with different results. Attached the Excel-file with my calculations. Best regards Raul _______________________________________ # Defines length of time-series ? nulldata 20 periodicity: 1, maxobs: 20 observations range: 1 to 20 ? setobs 1 1 --time-series Full data range: 1 - 20 (n = 20) # build stationary AR(3) error process for u ? scalar rho1 = 0.5 Generated scalar rho1 = 0.5 ? scalar rho2 = -0.3 Generated scalar rho2 = -0.3 ? scalar rho3 = 0.2 Generated scalar rho3 = 0.2 ? series u = 0 Generated series u (ID 2) ? series e = normal() Generated series e (ID 3) ? u = rho1*u(-1) + rho2*u(-2) + rho3*u(-3) + e Replaced series u (ID 2) ? print u e u: Full data range: 1 - 20 (n = 20) 0.000000 0.000000 0.000000 0.736134 0.389876 0.0831032 1.27225 0.296186 0.153867 -0.603212 -1.03987 -0.125745 1.05383 1.36702 1.38835 1.15469 0.0756820 0.396671 -0.373264 -0.802060 e: Full data range: 1 - 20 (n = 20) -0.191291 1.79901 0.222606 0.736134 0.0218093 0.109005 1.20043 -0.392982 0.370828 -0.845739 -0.751339 0.182452 0.925386 1.01036 1.04614 0.659854 -0.358562 0.427566 -0.779833 -0.511563 _____________________________________________________________ My calculations U e t-3 0 t-2 0 t-1 0 0 -0.191291 -0.191291 t+1 1.7033645 1.79901 -----Urspr?ngliche Nachricht----- Von: gretl-users-bounces(a)lists.wfu.edu [mailto:gretl-users-bounces@lists.wfu.edu] Im Auftrag von gretl-users-request(a)lists.wfu.edu Gesendet: Freitag, 10. Juli 2015 18:00 An: gretl-users(a)lists.wfu.edu Betreff: Gretl-users Digest, Vol 102, Issue 3 Send Gretl-users mailing list submissions to gretl-users(a)lists.wfu.edu To subscribe or unsubscribe via the World Wide Web, visit http://lists.wfu.edu/mailman/listinfo/gretl-users or, via email, send a message with subject or body 'help' to gretl-users-request(a)lists.wfu.edu You can reach the person managing the list at gretl-users-owner(a)lists.wfu.edu When replying, please edit your Subject line so it is more specific than "Re: Contents of Gretl-users digest..." Today's Topics: 1. generate AR (Raul Gimeno) 2. Re: generate AR (Sven Schreiber) 3. Re: generate AR (Riccardo (Jack) Lucchetti) 4. Re: generate AR (Ignacio Diaz-Emparanza) ---------------------------------------------------------------------- Message: 1 Date: Fri, 10 Jul 2015 09:46:51 +0200 From: "Raul Gimeno" <mrexito(a)vtxmail.ch&gt; To: <gretl-users(a)lists.wfu.edu&gt; Subject: [Gretl-users] generate AR Message-ID: <003101d0bae4$95777c50$c06674f0$(a)vtxmail.ch&gt; Content-Type: text/plain; charset="us-ascii" Hello I would like to generate AR, MA and ARMA processes. Is there any function available to do so? Would it be possible to include in the GRETL guide a note on how to generate simple time series? This could be of great help for beginners. I've tried to generate an AR(3) with the following script which doesn't work. Thank you for your help. Raul # seed set seed 89675430 # Generate an AR(3) process scalar rho1 = 0.5 scalar rho2 = -0.3 scalar rho3 = 0.2 loop 1000 # build stationary AR(3) error process for u series u = 0 series e = normal() u = rho1*u(-1) + rho2*u(-2) + rho3*u(-3) + e endloop -------------- next part -------------- An HTML attachment was scrubbed... URL: <http://lists.wfu.edu/pipermail/gretl-users/attachments/20150710/9b51a080/at tachment-0001.html> ------------------------------ Message: 2 Date: Fri, 10 Jul 2015 14:59:27 +0200 From: Sven Schreiber <svetosch(a)gmx.net&gt; To: gretl-users(a)lists.wfu.edu Subject: Re: [Gretl-users] generate AR Message-ID: <559FC1AF.9050707(a)gmx.net&gt; Content-Type: text/plain; charset=windows-1252 Am 10.07.2015 um 09:46 schrieb Raul Gimeno: There is 'varsimul' which you could use also univariate AR, but it's probably not the best way for your problem. Apart from that, specifying the data-generating process like you tried below is the right approach. "doesn't work" is a typical but almost useless component of problem reports. Please copy&paste the error message you're getting. This already looks quite good. Perhaps you don't have a dataset in place? Again, report your error message. -sven ------------------------------ Message: 3 Date: Fri, 10 Jul 2015 15:09:33 +0200 (CEST) From: "Riccardo (Jack) Lucchetti" <r.lucchetti(a)univpm.it&gt; To: Gretl list <gretl-users(a)lists.wfu.edu&gt; Subject: Re: [Gretl-users] generate AR Message-ID: <alpine.DEB.2.20.1507101509140.17956(a)ec-4.econ.univpm.it&gt; Content-Type: text/plain; charset="iso-8859-15"; Format="flowed" On Fri, 10 Jul 2015, Raul Gimeno wrote: Section 16.2 ------------------------------------------------------- Riccardo (Jack) Lucchetti Dipartimento di Scienze Economiche e Sociali (DiSES) Universit? Politecnica delle Marche (formerly known as Universit? di Ancona) r.lucchetti(a)univpm.it http://www2.econ.univpm.it/servizi/hpp/lucchetti ------------------------------------------------------- ------------------------------ Message: 4 Date: Fri, 10 Jul 2015 15:53:00 +0200 From: Ignacio Diaz-Emparanza <ignacio.diaz-emparanza(a)ehu.eus&gt; To: gretl-users(a)lists.wfu.edu Subject: Re: [Gretl-users] generate AR Message-ID: <559FCE3C.8080100(a)ehu.eus&gt; Content-Type: text/plain; charset=windows-1252; format=flowed El 10/07/15 a las 09:46, Raul Gimeno escribi?: For simulated data you need to inform gretl the length of your time series, with the first command 'nulldata 200' For example this reserves space for series with 200 obs. It may be useful also to inform that you plan to generate "time series" this may be done with the command 'setobs' in this way: 'setobs 1 1 --time-series' the first number is the seasonal periodicity (1 if you are making simulated data) the second one determines which is the first observation. The parameter --time-series makes posiible to use some gretl features specific for time series. Your script with these two commands works here. -- Ignacio D?az-Emparanza Departamento de Econom?a Aplicada III (Econometr?a y Estad?stica) Universidad del Pa?s Vasco - Euskalherriko Unibertsitatea, UPV/EHU Tfno: (+34) 94 601 3732 http://www.ehu.eus/ea3 ------------------------------ _______________________________________________ Gretl-users mailing list Gretl-users(a)lists.wfu.edu http://lists.wfu.edu/mailman/listinfo/gretl-users End of Gretl-users Digest, Vol 102, Issue 3 ******************************************* -------------- next part -------------- A non-text attachment was scrubbed... Name: AR(3).xlsx Type: application/vnd.openxmlformats-officedocument.spreadsheetml.sheet Size: 8933 bytes Desc: not available URL: <http://lists.wfu.edu/pipermail/gretl-users/attachments/20150711/fd3521f0/at tachment-0001.xlsx> ------------------------------ Message: 2 Date: Sat, 11 Jul 2015 11:00:52 +0200 From: Sven Schreiber <svetosch(a)gmx.net&gt; To: gretl-users(a)lists.wfu.edu Subject: Re: [Gretl-users] Gretl-users Digest, Vol 102, Issue 3 Message-ID: <55A0DB44.1040905(a)gmx.net&gt; Content-Type: text/plain; charset=windows-1252 Am 11.07.2015 um 10:10 schrieb Raul Gimeno: beginners. Menu: File -> script files -> exercise files (or Castilian or Basque translation thereof) only the numbering of the first 3 are different. Where do you expect gretl to store the t-1/ t-2 / t-3 starting values if not at the beginning? Does your excel sheet say "t-1" for the 3rd row or column? (no, of course not) cheers, sven ------------------------------ _______________________________________________ Gretl-users mailing list Gretl-users(a)lists.wfu.edu http://lists.wfu.edu/mailman/listinfo/gretl-users End of Gretl-users Digest, Vol 102, Issue 4 *******************************************