SVAR Restriction
by Olasehinde Timmy
Dear Prof,
I am aware that the code 'SVAR_restrict(&x, "C", 1, 2, 0)' is to inform
Gretl of the nature of the restriction to estimate. I also know that this
has to be repeated for several restrictions like in the model. However, I
consider this to be rigorous especially when a large matrix is involved.
Although, I know how a matrix can be created and used with the SVAR GUI, I
don't know how it can be used with the SVAR_restrict(&x, ) function.
Please, I need to be enlighten if this is possible or if I have to do the
imputation for each restriction.
Thanks.
4 months, 1 week
Announcement of pew package "PandasPort"
by Artur T.
Dear Gretl Community,
I am excited to announce the release of a new user-contributed package
named "PandasPort," inspired by the popular Python library Pandas. This
package is designed to provide a familiar and intuitive environment for
users transitioning from Pandas to Gretl for their data analysis and
econometric needs.
**Package Overview:**
PandasPort includes a comprehensive set of functions that mimic the
functionality of popular Pandas methods. The current focus is on
functions simplifying some data handling operations.
**Getting Started:**
You can find more details about the package and its functions here:
https://gretl.sourceforge.net/current_fnfiles/PandasPort.gfn
and here
https://github.com/atecon/PandasPort/blob/main/README.md)
Best
Artur
10 months, 2 weeks
IRF interpretation
by Lars Ahnland
Hi,
How am I to interpret the Gretl IRF charts (caculated from VEC) below? Is it correct to say that a unit (1) shock in the capital share granger-causes an increase of about 0,025 in the debt ratio from about five years? Or how? Thanks/Lars
[cid:2b0b04fa-a292-4d32-9c8f-e5afb2c3be50]
10 months, 2 weeks
non-linear restriction test
by Olasehinde Timmy
Dear Profs (Particually, Allin & Sven).
I hope my email finds you well. I noticed that Gretl doesn't incorporate
performing non-linear restriction tests on the estimate. Is there something
I am missing? If yes, please let me know. However, I would suggest that the
lords of this good software help those who don't understand coding by
incorporating this test just like the other packages into the next release
of Gretl.
Regards.
Timmy
10 months, 2 weeks
INFORMATION: Removal of "mat2data" package from the package server
by Artur T.
Dear Gretl users,
I am writing to inform you that the user-written package "mat2data" will
be removed from the Gretl package server today. This decision was made
because the functionality provided by "mat2data" has been superseded by
Gretl's built-in function "store" in recent versions.
The "store" function, which is now a part of Gretl's core functionality,
provides a more integrated and efficient way to store matrix data within
Gretl scripts. As a result, the "mat2data" package has become redundant
and will no longer be maintained on the package server.
However, for users who still wish to access the source code of
"mat2data" for reference or any other purpose, it will continue to be
available on GitHub at the following URL:
https://github.com/atecon/mat2data
Best regards,
Artur
10 months, 4 weeks
BVAR 0.3 now available
by Luca Pedini
Hi everybody,
a new version of BVAR is now available, the major changes include:
* a massive CPU time speed-up;
* a bug fix concerning forecasting with exogenous variables;
* a better integration with parallel_func >= 0.55 for MPI usage.
Please, feel free to download and have fun with it. Your feedback is always appreciated!
Best regards,
Luca
11 months
gretl 2024a released
by Cottrell, Allin
As usual, find gretl at gretl.sf.net.
The changes:
2024-04-05 version 2024a
- gretl "addons": integrate with releases on all platforms
- $sysinfo bundle: add gnuplot version as scalar ("gnuplot")
- "plot" command: update the help text and apply a fix for the
case of showing multiple bands
- "tsplots" command with matrix input: don't require a list
argument, plot all columns by default
- "gnuplot" command with --matrix and --time-series options:
show dataset time on x-axis if possible
- "gnuplot" command: add --y2axis option to specify placement
of a specifed y-variable on a second axis
show dataset time on x-axis if possible
- "info" command: add --to-file and --from-file options for
manipulating the description of a dataset
- "clear" command: add --all option to clear both function
definitions and all data
- "outfile" block: add a --decpoint option to enforce use of
decimal point (dot) for output within the block
- "freq" command: automatically switch to no binning in case
of few distinct values of the series argument
- "tsls" command: add a --matrix-diff option for the Hausman
test, using the method of Padadopoulos (Econometrics, 2023)
- "gmm" command block: support lists of series in extenso on
either side of an "orthog" statement
- "corrgm", "xcorrgm", "pergm" and "qlrtest" commands: make
these commands work properly in a "gpbuild" block
- "gmm" command: mark the --two-step and --iterate options as
mutually exclusive
- "loop foreach": support arrays and bundles that are located
inside other arrays or bundles
- "pkg install" command: support installation of data file
packages in tar.gz format from the gretl server
- "pkg query" command: show details of script and data files
from a package's "examples" directory, if present
- "pkg" command: add "run-sample" action to run the sample
script from a specified package
- "modeltab" command: add an --options flag to control
formatting via the command line
- New function fevalb(): a more flexible variant of feval()
- New function randstr(): gives a random hexadecimal string
of chosen length, to serve as a unique ID
- bcheck() function: make the second argument optional
- nobs() function: accept a list argument
- Fix broken backward compatibility in handling of backslash
followed by double-quote in string literals
- Fix bug: crash when plotting matrix data with the multiple
bands option
- Fix bug: restore support for reading JMulTi .dat files
- Fix bug: the "smpl" command with --dummy option could end
up broken after doing "Save data" in the GUI when there's
a sample restriction in place
- Fix bug: possible crash when a dbnomics download fails, if
invoked via the "data" command
- Fix bugs connected with estimation of panel data models via
pooled OLS with the --cluster option: the option was being
ignored in some cases and the "add" test was not working
- Fix bug: the symmetry checker for gretl matrices could fail
to flag asymmetry in some cases
- Fix bug: typeof() and typename() flagging an error in case
no object was found corresponding to the argument
- Fix bug: "modeltab" command flagging a spurious error in
some cases
- geoplot addon: fix obsolete usage of "outfile"
- GUI: fix for the "Dataset structure" mechanism when trying
to convert from side-by-side time series to panel
- GUI: apply some legibility fixes for dark GTK themes
- GUI: enable the advertised keystrokes in file "browser"
windows (bug #294)
- GUI function package editor: add support specific to the
editing of markdown help
- GUI script editor: improve handling of C-style comments in
auto-indentation
- GUI: make a newly installed data file package accessible
by reopening the relevant window; don't require a restart
of gretl
- gdt and gdtb data file specification: allow files which
contain no actual data series, just the implicit "const"
plus metadata (structure and number of observations)
- add a suite of unit tests to the gretl source tree
--
Allin Cottrell
Professor of Economics, Emeritus
Wake Forest University
11 months
Gretl User's guide State Space modeling - clarification
by Alecos Papadopoulos
On page 349 of gretl's user guide the state space model is defined as
Later, when presenting the state-space GUI (p. 369) we read that it
supports models of the form
My only question is about the time indices on the state vector in the
transition equation.
In the first model (p. 349), the starting values for the state variables
(alpha) should be for time t, and will also affect the first time point
of the measurement equation. In the second formulation (p. 369), these
starting values should be for time (t-1), they should lead to alpha
values for time t through the transition equation alone, which will then
affect the first time point of the measurement equation.
Which of the two does gretl do?
--
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
11 months
