May 2024 - Gretl-users - gretlml.univpm.it

by g s

Hi all I have a report about free to use menu based statistical software. Free To Use Statistical Software: Comparing Statistical Analyses https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4105959 This paper compares some basic analysis (frequencies, means by groups, correlations, OLS regression) among the different programs to make sure they all have the same results. I'm looking to add gretl, using the menu version. I found frequencies. Highlight variable of interest, then Variable and then Frequency Distribution. I'd like to do a means table, means of a continuous variable for each category in a categorical variable. I haven't found how to do that yet. I have a csv version of the data set here https://drive.google.com/file/d/11WIET3s4eMHsB6JQ6hOQBx0SKquGRKKw/view?us... One variable is population, which is population by country. Another variable is region, that is, world region. All of the countries are included in some region. How do I get mean population by world region? Thanks Gene

4 months, 1 week

6
28
0 / 0

Kalman Filter together with maximum likelihood - clarification about the Variance-Covariance things

by Alecos Papadopoulos

I realized that I am a bit confused as to what happens with the various VCV matrices when Kalman Filter is used together with maximum likelihood. Assume a time-invariant state space model. What I understand is the following: The Kalman Filter will run as usual and will provide the various VCV estimates as described in Ch. 36 of the user's guide, based, in the end, on the final ML estimates to obtain the residual series (the etas and the epsilons). But at the same time, we may have asked the mle to estimate also the elements of the VCV matrices, (see eg. the ARMA estimation example Listing 36.1). This will give us another, different estimate of the VCV matrices... or will this agree with the KF estimates above, due perhaps to the fact that this is Normal mle that we necessarily assume? I am asking in case somebody knows already the answer. If not, I will probably run various simulations to see what happens. -- 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

4 months, 3 weeks

3
2
0 / 0

Install gretl via snap or flatpak

by Carlos Andrade

Hello, everyone. I'm a Debian bookworm user. Is there any way to install the latest version of Gretl via snap or flatpak? Atenciosamente, Carlos Antonio Soares de Andrade Economista e Consultor de Empresas Telefone: (83) 9 98117113

4 months, 3 weeks

3
2
0 / 0

Install gretl via snap or flatpak

by Carlos Andrade

Hello, everyone. I'm a Debian bookworm user. Is there any way to install the latest version of Gretl via snap or flatpak? Atenciosamente, Carlos Antonio Soares de Andrade Economista e Consultor de Empresas Telefone: (83) 9 98117113

4 months, 3 weeks

1
0
0 / 0

Question about the Kalman Filter - MLE combination

by Alecos Papadopoulos

When we combine the Kalman Filter with the mle command, we use the "kfilter" or the "ksmooth" function as a success/failure check for KF, and if we're good, we tell the mle to have a look at the series with the likelihood contributions, and proceed with parameter estimation. We automate this by using a conditional statement on the mle line itself (as shown e.g. in the user guide, p. 362). In no-KF mle, this conditional statement is often used to impose constraints on the parameters (like positivity of variances). I understand that simple non-negative constraints can be imposed in other indirect ways, but I have to impose bounds on the estimated parameters like "0<alpha<1". So can I somehow combine the naked mle "check" syntax with the KF-success syntax into one, say <hansl> mle logl ERR && CHECK ? NA : kb.llt .... ERR = kfilter(&kb) scalar CHECK = (alpha>0) && (alpha<1) params alpha end mle </hansl> ...or do I need something more elaborate? (maybe there is an issue with the fact that good news for ERR is when ERR=0 while good news for CHECK is when CHECK = 1, if I understand correctly?) -- 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

4 months, 4 weeks

3
3
0 / 0

Problem when using a list

by Rigoberto Perez Suarez

Hello, I have been a Gretl user for many years, and I would like to thank you for the important development you have promoted during this time. We have observed a typo since 2023b version when calculating rates using a list. More specifically, for the individual series we compute without problem: T=round(10000*(x/x(-1)-1))/100 However, when we use a list: list l=y1 y2 y3 list l_t=null loop foreach x l genr t$x=round(10000*(l.$x/l.$x(-1)-1))/100 list l_t+= t$x endloop This code does not work properly. It is necessary to include a new parenthesis in the quotient (l.$x/l.$x(-1)) (which would not be necessary) to perform the operation correctly. Thank you and best regards Rigoberto Pérez

4 months, 4 weeks

5
12
0 / 0

gretl 2024b released

by Allin Cottrell

This is mostly a bug-fix release, but with some new functionality and improved documentation on several points. 2024-05-21 version 2024b - "gridplot" command: add a --title option - "clear" command: add an --all option - instrings() function: add optional boolean argument to get a simple boolean return value - typeof() function: functionality is extended to cover hansl expressions in general - exists() function: recommended usage is restricted to top- level identifiers, but backward compatibility is preserved for the present - new function binperms() for binary permutations - Testing for equality via "==" and "!=": extend this to cover arrays and bundles - help files: clarify the help for some commands and improve formatting - $sysinfo bundle: add "stack_size" - mrw (Mankiw-Romer-Weil) dataset: rename "inv" as "i_y" - Fix bug: crash on replacing a single character in a string variable, when the replacement UTF-8 character takes up more bytes than the original - Fix bug: potential crash when using the "smpl" command on a dataset that is already subject to random resampling - Fix bug: possible confusion in parsing lag specifications for list members, as in "list.vname(-1)" - Fix bug: possible interference of options passed in "plot" with those passed to "gnuplot" - Fix bug: crash in 32-bit gretl for Windows when trying to read gdtb data files created on a 64-bit system - Function packages: validate gfn files using an XML schema rather than a Document Type Definition - GUI, function packages: further extensions to the "ui-maker" functionality, plus minor fixes for the function-call dialog - GUI: support the --preserve-panel option in the dialog box for sub-sampling - GUI: support the Gamma distribution under /Tools/Distribution graphs - GUI: fix the "Packages" entry under Help - GUI: ensure that all fonts scale on zoom in/out in help - GUI: add more choices for plot scaling - GUI: improvements to the regls dialog - Internals: economize stack usage in case of nested function calls - 64-bit Windows build: increase stack size to 8 MiB (as per Linux and macOS) - regls addon: bug fixes and improved documentation Allin Cottrell

4 months, 4 weeks

1
0
0 / 0

Graph output

by Cristián Arturo Ducoing Ruiz

Hi there, I did some graphs with the new gridplot function ( https://github.com/gretl-project/material-on-gretl/wiki/Plotting#gridplot) and the visible output is quite nice: [image: image.png] However, when I saved the same image this is the output I got. [image: TestGraph.png] I know in pdf the output is customizable, but I needed it in png. Any tips? I'm using the latest gretl version and windows 11 -- Atte. Cristián Arturo Ducoing Ruiz

5 months

2
4
0 / 0

Possible bug in yahoo.get (spanish)

by Cristián Arturo Ducoing Ruiz

Hi there, I was trying to get data from Yahoo using the package yahoo_get and after several attempts to get the data, I always got the same error message ("error de datos", data error in english). By default the configuration was in Spanish. I changed the preferences to English and using the same code, I got immediately the data requested (MSFT) include yahoo_get.gfn series msft = yahoo_price("MSFT", 1) MSFT imported ok Generated series msft (ID 2) Im using windows 11 and the latest gretl version (2024a) Best regards -- Atte. Cristián Arturo Ducoing Ruiz

5 months

3
7
0 / 0

gretl release coming up

by Cottrell, Allin

We've fixed a number of gretl bugs lately, and although they're unlikely to affect most users we'd rather not have them lingering on. So we're going to make a new release, 2024b, sooner than we usually would, probably early next week. This is just to say that if anyone is thinking of updating translations this would be a good time to do so. Plus, we'd be grateful if people could try out the current snapshots -- they're up to date as of today -- and report any issues they find. Thanks, Allin Cottrell

5 months, 1 week

1
0
0 / 0

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

2010

2009

2008

2007

2006

2005

2004

Gretl-users May 2024