Gnu Regression, Econometrics and Time-series Library

Is a cross-platform software package for econometric analysis, written in the C programming language. It is free, open-source software. You may redistribute it and/or modify it under the terms of the GNU General Public License (GPL) as published by the Free Software Foundation.

gretl conference

The most recent biennial gretl conference (the eighth) took place in Gdańsk on June 15-16, 2023. The 2021 conference was slated to be in London, but due to the Covid pandemic it was held online via Zoom. Previous conferences took place in Naples (2019), Athens (2017), Berlin (2015), Oklahoma City (2013), Toruń (2011) and Bilbao (2009). For further info see gretlconference.org. Our thanks go to all the organizers of these conferences.

Features

• Easy intuitive interface (now in French, Italian, Spanish, Polish, German, Basque, Catalan, Galician, Portuguese, Russian, Ukrainian, Turkish, Czech, Traditional Chinese, Albanian, Bulgarian, Greek, Japanese and Romanian as well as English)

• A wide variety of estimators: least squares, maximum likelihood, GMM; single-equation and system methods; regularized least squares (LASSO, Ridge, elastic net)

• Time series methods: ARIMA, a wide variety of univariate GARCH-type models, VARs and VECMs (including structural VARs), unit-root and cointegration tests, Kalman filter, etc.

• Limited dependent variables: logit, probit, tobit, sample selection, interval regression, models for count and duration data, etc.

• Panel-data estimators, including instrumental variables, probit and GMM-based dynamic panel models

• Output models as LaTeX files, in tabular or equation format

• Integrated powerful scripting language (known as hansl), with a wide range of programming tools and matrix operations

• GUI controller for fine-tuning Gnuplot graphs

• Facilities for easy exchange of data and results with GNU R, GNU Octave, Python, Julia, Ox and Stata

• Parallelization via MPI (details)

• Support for mixed time-series frequencies (MIDAS) (details)

• Support for machine learning via LIBSVM (details)

Besides gretl's core functionality, several addons and numerous contributed function packages are available. See Contributing to gretl below.

Data formats

Supported formats include: own XML data files; Comma Separated Values; Excel, Gnumeric and Open Document worksheets; Stata .dta files; SPSS .sav files; Eviews workfiles; JMulTi data files; own format binary databases (allowing mixed data frequencies and series lengths), RATS 4 databases and PC-Give databases. Includes a sample US macro database. See also the gretl data page.

Download

Gretl for MS Windows can be found here, and gretl for macOS here.

For Linux, you have:

If you want to compile gretl from source, the current source package is gretl-2024c.tar.xz, and you may want to check out gretl's dependencies. However, if you're on Linux and want to build current gretl, the tarball buildgretl.tar.gz will automate most of the work (we assume you know what you're doing, but a README file is included).

The time-series analysis programs X-13-ARIMA and TRAMO/SEATS are available in a form suitable for use with gretl on Linux, as follows.

Look here for system requirements and installation guide.

Gnuplot

Gretl calls gnuplot to generate graphs. We require gnuplot version 5.2 (released in September 2017) or higher. See gnuplot.sourceforge.net. The gretl packages for MS Windows and OS X include a gnuplot version that works well with gretl. Reasonably current Linux distributions should also offer a suitable version of the program.

Manual

The gretl manual comes in three PDF files, a User's Guide, a Command Reference and a Hansl primer. English versions of these, formatted for U.S. letter-size paper, are included in the gretl source package and binary distributions. Gretl will access other available versions on demand, via the Internet. You can also find the manual files here.

In addition the Gretl Command Reference and Gretl Function Reference are available in HTML format.

Getting help, reporting bugs

If you use gretl you may wish to join the gretl-users mailing list. This is a moderate-volume list where people request and offer help, discuss new features and so on. There's also a gretl-announce list; this is a read-only list which sends out announcements on the occasion of new releases of gretl.

You can submit bug reports and feature requests using the SourceForge Tracker system.

Contributing to gretl

Do you have ideas or code that you'd like to contribute to gretl? If so, we'd be very pleased to hear from you. You should probably join the gretl-devel mailing list.

The most obvious way of contributing your expertise to gretl development is by writing a function package (using gretl's scripting language, hansl). You can see a listing of current packages here. A quick Guide to producing function packages is available (thanks, Stefano Fachin!).

If by any chance you're a C coder then contributions to the underlying gretl library would also be welcome. The only non-negotiable requirement on C code that can be contributed to gretl is that you must be willing to have it appear under the GNU General Public License (GPL), that is, you must be comfortable with having the source released.

Git access and browsing

You can find the gretl git repository here. Notes on basic usage of git are available here and full documentation at git.scm.com.

Acknowledgements

First of all, thanks to Ramu Ramanathan (1936-2013). Ramanathan was Professor of Economics at UCSD and author of Introductory Econometrics. Gretl's origins lie in Ramanathan's open-sourcing of the C code for his econometrics program "ESL".

Many people have sent in useful bug reports and suggestions for gretl's development. We are particularly indebted to Ignacio Díaz-Emparanza, Tadeusz Kufel, Pawel Kufel, Dirk Eddelbuettel, Sven Schreiber and Andreas Rosenblad. A. Talha Yalta plays a helpful role in scrutinizing and reporting on gretl's numerical accuracy.

Many thanks to Ignacio Díaz-Emparanza, Susan Orbe, Michel Robitaille, Florent Bresson, Cristian Rigamonti, Tadeusz and Pawel Kufel, Markus Hahn, Sven Schreiber, Hélio Guilherme, Henrique Andrade, Alexander Gedranovich, Talha Yalta, Y. N. Yang, Pavla Nikolovova, Jan Hanousek, Artur Bala, Manolis Tzagarakis, Ioannis Venetis, Vitalie Ciubotaru, Mihaela Nicolau, Oleh Komashko and Juan Estévez for their work in translating gretl.

Thanks to William Greene, author of Econometric Analysis, for his permission to include in the gretl package some datasets relating to interesting examples in his text.

Thanks to the good people on the comp.lang.c of old and gtk-app-devel-list@gnome.org for expert advice on many issues. Thanks to Richard Stallman of the Free Software Foundation for all his work in developing and promoting free software, and more specifically for agreeing to "adopt" gretl as a GNU program.

Allin Cottrell, Wake Forest University

Riccardo "Jack" Lucchetti, Università Politecnica delle Marche

Last modified: 2024-10-21