January 2013 - Gretl-devel - gretlml.univpm.it

by andreas.rosenblad＠ltv.se

Dear gretl developers, If possible, I would like to see the following features included in gretl and available form the GUI, to make it more usable: Univariate tests: *Z-test of means for paired data *McNemars test *Kruskal-Wallis test *Friedman's test *Jonckheere-Terpstra test For duration data: *Kaplan-Meier curves plot *log-rank test *Cox regression Regression models: *conditional logistic (logit) regression *generalized estimating equations *generalized linear mixed models Any chances of any of these being included? Best regards, Andreas Rosenblad

12 years, 6 months

4
4
0 / 0

Help files in HTML

by Allin Cottrell

One useful suggestion that came up lately was to make the gretl help files available in HTML on the web, so that google can index them. I've now put a "proof of concept" version of the Command and Function Reference files at http://gretl.sourceforge.net/gretl-help/ -- Allin Cottrell Department of Economics Wake Forest University, NC

12 years, 9 months

2
2
0 / 0

coint2 and warnings

by Andreas Noack Jensen

When I extract the p-values from coint2 with restricted exogenous variables I receive a warning and a column of nans ? coint2 4 endo; d_IAU; IAU --crt --silent ? eval $pvalue 0,021269 nan 0,88179 nan 0,68159 nan Warning: generated non-finite values Is this intended? Can I suppress the warning? Best Andreas

12 years, 10 months

3
2
0 / 0

zero dimension matrix arithmetic

by Andreas Noack Jensen

I have a function which takes lists as argument and then tranform them to matrices. However, sometimes the lists are null and I therefore get a 0x0 matrix which is okay but when I concatenate with a nx0 matrix I get a 0x0 matrix. I think a nx0 matrix is more reasonable but I agree that things are fishy here. An example is ? eval ones(5,1)~{null} 1 1 1 1 1 ? eval ones(5,0)~{null} matrix is null (0 x 0) What do you say? Would it cause problems elsewhere if the latter was 5x0? Or should I do something completely different in order to avoid the situation? Best Andreas

12 years, 10 months

3
2
0 / 0

website translations

by Allin Cottrell

Hassle, hassle! Sorry, but many of the translations of pages on the gretl website at sourceforge lag the English versions by months or years. Some of the updates to the English pages are fairly trivial, but some are quite substantive (e.g. revision of the pages relating to gretl on OS X). Which raises the question of whether non-native English speakers are better off looking at an up-to-date page in English or an out-of-date page in their own language. I'd be very glad to receive suggestions on the best way of keeping the translations reasonably up to date. As you know, the gretl web pages are in CVS. It's possible to set up a notification email when certain parts of CVS change, but I think that may be non-trivial to get right. I guess I could set up a sort of website bulletin, such that every so often (say, every 3 months) I send out an email noting pages that have changed "significantly". But, given the number of other things I have to do, I'd prefer if someone can suggest something else! Allin Cottrell

12 years, 10 months

5
15
0 / 0

Strings not marked for translation

by Henrique Andrade

Dear Allin, I found some strings that I think are not marked for translation: 1. "No such file or directory" When open a non-existing file. 2. "Scale is at maximum" In a Gnuplot graph: Best regards, Henrique Andrade* *

12 years, 10 months

3
13
0 / 0

Signalling

by Riccardo (Jack) Lucchetti

Folks, allow me to link a short and interesting read: http://seanjtaylor.com/post/39573264781/the-statistics-software-signal In short, this guy characterises software users of several math/stat packages. I just have a few observations, on which I'd like to hear as many opinions as possible: 1) We're not on the list. As I've been saying many times over the years, gretl being listed as one of the mainstream alternatives must be one of our priorites and we need to think hard on how to achieve greater and greater visibility. We've come a long way since 2009 (http://ideas.repec.org/h/ehu/ehucha/01-03.html), but in the average guy's percetption, we still are a minor player compared (say) to Stata. For example, one of the thigs we need most badly is, IMO, the Hansl manual. 2) If we were on the list, what kind of comments would you expect to see? ------------------------------------------------------- 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 -------------------------------------------------------

12 years, 10 months

10
34
0 / 0

smartphones

by Sven Schreiber

Hi and happy new year, we briefly talked about the future of gretl on non-PC devices, so I allow myself to point to this, just as fyi: http://www.canonical.com/content/ubuntu-comes-phone-beautifully-distilled... Of course, having an interface and a Linux kernel isn't enough to get all the number-crunching capabilities of PC hardware, I'm aware of that. And of course, Ubuntu is neither the only nor the first player to try cross-device unification. cheers, sven

12 years, 10 months

2
1
0 / 0

new in CVS

by Allin Cottrell

Something people might like to test: in CVS I've added Bruce Hansen's asymptotic p-values for the "qlrtest" command, and also configured it so that if the original model was estimated with the --robust flag, the sup-Wald test uses the robust variance matrix. As for the issue I mentioned a week ago (the dating of the "break"), I notice that Hansen defines it the same way gretl does (the break period being the first period of the "new regime") so I'm not going to change that at present. Allin

12 years, 10 months

2
2
0 / 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

2010

2009

2008

2007

2006

Gretl-devel January 2013