Gretl-users November 2008

gretl-users@gretlml.univpm.it

22 participants
26 discussions

by Sven Schreiber

Hello, it's been a while since I compiled the cvs version, so today was the first time I noticed the "you can also build the pdf docs" part of the configure output (on Ubuntu 8.04). I tried that but got errors complaining about mathtime.sty missing. I'm using the standard Texlive distro packaged in/for ubuntu, no special stuff AFAIK. For some background on mathtime in texlive see http://bugs.debian.org/cgi-bin/bugreport.cgi?bug=425460. Could the dependency on the mathtime package be removed? I'm using this latex installation for lots of math without errors, so my first guess would be that it's possible. thanks, sven BTW, the list has been quiet recently, is that good or bad? Oh, and another thing, I wanted to log in to the gretl area at sourceforge, but couldn't get a secure https connection, only http. Has anybody else noticed that?

16 years, 4 months

7
15
0 / 0

Newbie questions about using systems in Gretl

by jan.limbers＠prognos.com

Hello! Please forgive me if the following questions are a little bit "stupid", but as I mentioned, I'm a newbie... My aim is to build up a little macro-model like the "klein.inp", using ols estimations, and to do forecasts with it. Some questions arise hereby: 1. In the command reference, page 51 (A4-Version) about using systems it is mentioned that identities are needed if FIML estimation is used. But also with ols or other estimations the system has to know how to create the forecast values of derived variables which are not estimated inside the system. Did I miss anything in the reference? And I guess that also with ols-estimation I have to declare the endogenous variables? 2. Which command is necessary if I want the system to do forecasts for the system as a whole? In the graphic interface there is the possibility to select only one estimated variable, but as you know the clue of using systems is all variables are estimated simultaneous in mutual dependency... Thank you for your help, regards, Jan Limbers Prognos AG - Basel-Stadt HRA CH-270.3.003.262-6 Geschaftsfuhrer: Christian Bollhoff Prasident des Verwaltungsrates: Gunter Blickle

16 years, 4 months

4
7
0 / 0

Interrupted Time Series (Intervention) Analysis Utilizing ARIMA

by Charles R. Partridge

Greetings, I'm a newcomer to Gretl, and I'm looking for tutorials or citations that focus on how to analyze the effects of an intervention, utilizing the ARIMA with data from an interrupted time-series design. Thanks in advance! Regards, Charles R. Partridge, Ph.D. Independent Evaluation Consultant C.H.I.P. Evaluation Consulting Columbus, Ohio (614) 205-5079 cpartridge(a)chipeval.org

16 years, 4 months

2
1
0 / 0

Re: [Gretl-users] any documentation on error message

by mchavez＠fundacionidea.org.mx

You are heroic Allin. Really devoted. . .cheers. Manuel. ------Mensaje original------ De: Allin Cottrell Remitente: gretl-users-bounces(a)lists.wfu.edu Para: zzh5460(a)yahoo.com Para: Gretl list Responder a: Gretl list Enviado: 7 Nov 2008 20:15 Asunto: Re: [Gretl-users] any documentation on error message On Fri, 7 Nov 2008, Rebecca Zhang wrote: > Here is what I mean: > > I have time series (daily) data for about 50 portfolios. I want to calculate the mean over time for each of the portfolios. And store them in below way: > > portfolio 1 mean 1 > portfolio 2 mean 2 > portfolio 3 mean 3 > ... > > I am able to get statics summary for all the portfolios. (That > includes mean and std) How to store these statics for each > portfolio in a way convenient to further processing? I think that Jack and I have told you that: how to turn a list of statistics into a data series. Take either of our procedures and try it. Allin Cottrell _______________________________________________ Gretl-users mailing list Gretl-users(a)lists.wfu.edu http://lists.wfu.edu/mailman/listinfo/gretl-users Enviado desde mi oficina móvil BlackBerry® de Telcel

16 years, 4 months

1
0
0 / 0

Re: Problem installing from cvs in Ubuntu 8.04

by Gordon Hughes

Just for information, I have been able to compile recent versions of gretl under Ubuntu 8.04 and use a functioning version of R with a much more limited set of libraries than those that you list in your last e-mail. Based on my experience the minimum requirements are: libblas3gf (1.2.1.3ubuntu4) libblas-dev (ditto) liblapack3gf (3.1.1-0.3ubuntu2) liblapack-dev (ditto) plus the gfortran and gfortran2 compilers/libraries that you list. In the past I have encountered difficulties when too many versions of atlas, blas, lapack or fortran are installed, because the compiler or Ubuntu appears to get confused in seeking the appropriate libraries. Gordon

16 years, 4 months

3
2
0 / 0

fyi (semi-OT): secure sourceforge login

by Sven Schreiber

Hi, maybe this is interesting for other users as well: currently the main login page to sourceforge is not secure (http instead of https). There is already a bug report about this (tracker item 2166495): http://sourceforge.net/tracker/index.php?func=detail&aid=2166495&group_id... Strangely, the SF team think this is of "moderate" importance. Maybe they simply have too much to do right now. A workaround is provided by another user "mkc": "I did discover a workaround: If you type garbage into the initial login box, a secure "try again" page is presented." cheers, sven

16 years, 4 months

1
0
0 / 0

← Newer
1
2
3
Older →

2025

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

2010

2009

2008

2007

2006

2005

2004

Gretl-users November 2008