June 2025 - Gretl-users - gretlml.univpm.it

by Brian Revell

Is there any reason why recursive forecasts cannot be generated and included in the ARIMA option for univariate modelling forecasts (together with their confidence intervals ) when no exogenous variables have been included in the specification Clearly post sample data the MA terms would drop out. Brian

2 weeks

2
1
0 / 0

issues compacting frequency from hourly to daily

by Sven Schreiber

Hi, I have an hourly dataset which I want to transform (compact) to daily data. I'm going to describe some problems, first using the GUI, then with a concrete script example (but different problems). GUI: I applied the dataset structure wizard from Data / Reduce frequency with what seemed to be a success at first, by choosing "to 7-day daily" and averaging as the compaction method. However, it then turned out that the data compaction didn't seem to be correct. Notice that the dataset starts not at midnight, but in the middle of the first day, so during the first day there are less than 24 obs; maybe that matters. Specifically, I created a "check" series that only holds 1 during the hours of the first day. I would expect that that first day in the daily data then gets a 1, but instead it got a 0. There also seemed to be other artefacts afterwards. Script example: <hansl> nulldata 100 setobs 24 10:4 --time-series # hourly, starts at day 10, hour 4 series day = $obsmajor series hour = $obsminor series check = day==10 ? 1 : 0 # is 1 for less than 24 hours dataset compact 7 # error, not supported </hansl> First, it's funny that the compaction "worked" in the GUI, but the script reaction is that it's not supported. But maybe the latter is more appropriate, given my problems before. Next, if instead of "dataset compact 7" I use "dataset compact 1", there's no error, but gretl now thinks it's an annual dataset, but my "check" variable still doesn't get the 1 value for the first compacted obs. thanks sven

1 month

1
1
0 / 0

Repeatable Gretl crash

by Fred Engst

Hi Allin and the gretl team I’ve discovered a new situation where gretl crashes. I’m using the "latest release (Jun 5, 2025) gretl-2025b-macos-intel.pkg” When I save a file without navigating throw the file manu, and instead by dragging a file from the folder where I wanted to save, to the save window as a way to let gretl knows the folder that I’m saving to, the bottem of the saving window missing the file format, instead of showing .gdt, so gretl doesn’t know the file format that I’m going to save and then it crashes. This is repeatable. 1 let gretl open a file like cars.gdt in POE4 folder 2 select “file”-> “save data as” 3 dragg a file from the folder that I wanted to save, to the gretl save window. Sometimes it crashes right away, sometimes it crashes when I hit the save button. Here is the first few lines of the crash report: ------------------------------------- Translated Report (Full Report Below) ------------------------------------- Process: gretl [23418] Path: /Applications/Gretl.app/Contents/MacOS/gretl Identifier: net.sourceforge.gretl Version: 2025b Code Type: X86-64 (Native) Parent Process: launchd [1] User ID: 502 Date/Time: 2025-06-24 07:32:55.5588 +0800 OS Version: macOS 14.7.4 (23H420) Report Version: 12 Bridge OS Version: 9.3 (22P3051) Anonymous UUID: D0C17D83-C8DE-88A8-08E7-19E42233A73F Sleep/Wake UUID: 92D70123-4A7D-4756-8B2B-077DC0B0EBB4 Time Awake Since Boot: 120000 seconds Time Since Wake: 2945 seconds System Integrity Protection: enabled Crashed Thread: 0 Dispatch queue: com.apple.main-thread Exception Type: EXC_BAD_ACCESS (SIGSEGV) Exception Codes: KERN_INVALID_ADDRESS at 0x0000000000000000 Exception Codes: 0x0000000000000001, 0x0000000000000000 Termination Reason: Namespace SIGNAL, Code 11 Segmentation fault: 11 Terminating Process: exc handler [23418] VM Region Info: 0 is not in any region. Bytes before following region: 4517265408 REGION TYPE START - END [ VSIZE] PRT/MAX SHRMOD REGION DETAIL UNUSED SPACE AT START ---> __TEXT 10d400000-10d51a000 [ 1128K] r-x/r-x SM=COW /Applications/Gretl.app/Contents/MacOS/gretl attached is the full system crash report:

1 month, 2 weeks

2
1
0 / 0

Gretl-2025b

by Dhanasekaran Kuppusamy

Hi Gretl users, The following code is not working in the new version of Gretl-2025b. But when I use the previous version of the Gretl it gives the results. What is the problem with the following code? What is the solution to this problem? string F_Bound_LS= sprintf"F_Bound_Calculated : %.4f\n F_Lower_Bound_I[0]: %.4f\n\ F_Upper_Bound_I[1]: %.4f\n",F_Calc_Bound_LS, F_B_I0,F_B_I1) print "@F_Bound_LS" string t_Bound_LS= sprintf"t_Bound_Calculated : %.4f\n t_Lower_Bound_I[0]: %.4f\n\ t_Upper_Bound_I[1]: %.4f\n",t_Calc_Bound_LS, t_B_I0,t_B_I1 print "@t_Bound_LS" Thanks in advance. Dhanasekaran

1 month, 2 weeks

3
7
0 / 0

Using sprintf() in gnuplot command

by Artur T.

Hi all, I just stumbled over the following trying to add a title to a plot: <hansl> set verbose off nulldata 10 series y = normal() scalar a = 0.98 gnuplot y --time-series --output=display \ {set title sprintf("Some statistics = %.2f", a);} <> As you can see, I tried to apply the handy expression using the sprintf() function. It does _not_ provike an error, but the value of `a` is printed as `nan`. Is sprintf() actually supported? If not, I guess an error should be thrown. If it actually is supported, the right value of a should be printed. Thanks, Artur

1 month, 3 weeks

3
3
0 / 0

How can I eradicate a function permanently?

by Paolo Chirico

Dear all, I have just deleted a package I created for testing. However, the main (public) function contained in the package seems to still exist, and gretl prevents me from creating a new one with the same name. I have even uninstalled gretl and installed the latest version, but the function still exists even though the package no longer appears in the package list. How can I eradicate it permanently? -- Paolo Chirico RU e Prof.Agg. di Statistica Economica Università del Piemonte Orientale Dip. di Giurisprudenza e Scienze Politiche, Economiche e Sociali (DIGSPES) Alessandria, Italia -- Questa email è stata esaminata alla ricerca di virus dal software antivirus AVG. www.avg.com

2 months

4
8
0 / 0

Downloadable Function Packages

by Brian Revell

For those Gretl users who rely entirely on the GUI (and may be of an age now unwilling to learn a new programmimg language}. It would be helpful to be able to filter the extensive and admirable list of Function Packages by those that will attach to the GUI (and if so, where).. Thanks for all you guys do Brian *Brian Revell*

2 months

2
1
0 / 0

Package updates (May 2025)

by Riccardo (Jack) Lucchetti

Dear all, this message is to inform the community about the activity in our function package repository: during the month of May 2025, two packages were updated to a new version: "DiebMar", by Giulio Palomba (Diebold-Mariano test for predictive accuracy) "uniFCextensions", by Sven Schreiber (Extensions for univariate forecast models) I you'd like to know more on these packages, or simply find out what's new, the best way is to open the packages page (https://gretl.sourceforge.net/cgi-bin/gretldata.cgi?opt=SHOW_FUNCS) and click on the package name or on the [doc] tag if available. Download and enjoy! ------------------------------------------------------- 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 -------------------------------------------------------

2 months

1
0
0 / 0

gretl4py 0.2 released

by Marcin Błażejowski

Dear Gretl Community, It’s been almost exactly 11 months since I started a new gretl-related project: *gretl4py*. Over this time, I’ve spent countless hours writing and testing the module, learning a lot about the inner workings of *libgretl*, and rediscovering my long-dormant C++ skills. (After 20 years away from the language, I found myself in a new, much better world! 😄) Today, I’m happy to announce the release of *version 0.2*, now available via PyPI for the three major operating systems: Windows, macOS, and Linux. This means you can install it simply by running: /python -m pip install gretl4py/ Please note that the official PDF documentation is slightly outdated, as it mostly refers to version 0.1. For a better starting point, see the simplified documentation at: 🔗 https://pypi.org/project/gretl4py/ You can also look at example scripts here: 🔗 https://sourceforge.net/p/gretl/gretl4py/ci/v0.2/tree/demo/ 🔗 https://sourceforge.net/p/gretl/gretl4py/ci/v0.2/tree/gretl/examples/ At this point, I’d like to thank everyone who has contributed in some way to the gretl4py project—especially: * *Allin Cottrell*, for helping me integrate libgretl functionality into the bindings, * *Riccardo (Jack) Lucchetti*, for testing and inspiring ideas about what could be added and how, * and *Federico Fiorani*, for his contributions to the first version of the package. Of course, any remaining bugs are my responsibility. If you find any, or have questions about the package, don’t hesitate to speak up! With best regards, Marcin

2 months

1
0
0 / 0

Panel-data sample manipulation-transformation

by Alecos Papadopoulos

I went through the available panel-data functions in gretl and what I describe below does not appear to be implemented. I also have difficulty imagining how I could do it through a user-defined function because I do not understand whether, and how, the variant of panel-data structure (stacked v_1, stacked v_2, or based on variables etc), may need to be taken into account or not. Also, how the case of an unbalanced panel could be handled (which is indeed my case - and as Bruce E. Hansen writes "unbalanced panels complicate computer programming"...) I would appreciate any suggestions. Let a balanced panel data sample {y_{it}, x_{it}}, i=1,...,N, t=1,...,T I want to transform the sample by subtracting from each data point the related group-mean, i.e. the mean value of the same (same by nature) variable across the dimension i=1,...,N Namely to perform the operation z_{it} = x_{it} (-) (1/N)*sum_{i=1}^N [x{it}], i.e. z_{it} = x_{it} (-) (1/N)*[x_{1t} + x_{2t} + ... + x_{Nt}] and the same for the "y" variable, and any other variable in the sample. Ideally, this has to work for both balanced and unbalanced panels., i.e. when the "N" may differ in each t time period. -- Alecos Papadopoulos PhD Affiliate Researcher Dpt of Economics, Athens University of Economics and Business Foundation for Economic and Industrial Research (IOBE) web: alecospapadopoulos.wordpress.com/ ORCID:0000-0003-2441-4550

2 months

4
6
0 / 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

2010

2009

2008

2007

2006

2005

2004

Gretl-users June 2025