(no subject)
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
4 months, 4 weeks
Package updates (December 2024)
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 December 2024, 3
packages were updated to a new version:
"graphlasso", by Sven Schreiber (graphical Lasso --- l1 shrinkage for
covariance matrices)
"lomackinlay", by Allin Cottrell and Sven Schreiber (Lo-MacKinlay
variance ratio test for determining if a time series is a random walk
process)
"BACE", by Marcin Błażejowski and Jacek Kwiatkowski (Bayesian Averaging
of Classical Estimates)
I'll reserve a special mention for the "graphlasso", which now uses a
new internal function to speed up computation.
Sorry if this message comes relatively late in the month, but I was away ;)
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
-------------------------------------------------------
7 months, 2 weeks
ARIMA on log transformed data
by dbrilakis＠yahoo.gr
Hi, I found that my data become stationary (after differentiate) the log data with best ARIMA(p,d,q) How do I rebuilt the ARIMA forecast to the origina scale before log?
Tanks in advance
7 months, 3 weeks
frequent macOS popup about the "otool" command
by Ron Cronovich
Greetings, from Kenosha, WI USA.
Last month, I wiped my Mac's hard drive and reinstalled the latest version of macOS, which I do every year without incident.
Since then, whenever I run GRETL, macOS gives me a popup that says
The "otool" command requires the command line developer tools. Would you like to install the tools now?"
There are two options: Cancel, and Install. I always click on Cancel and GRETL runs just fine on my computer, as always.
This happens literally every time I run GRETL. If I completely quit GRETL and immediately start it again, I get the same popup.
I'm running GRETL version 2025a, which is the latest version. My macOS is up to date, as well.
GRETL seems to work fine without the command line developer tools. I'd like to stop getting this popup prompt that keeps asking me the same question.
I'd be grateful for any suggestions.
Ron
7 months, 4 weeks
Introduction to hansl Programming Course
by Artur T.
Dear gretl Mailing List,
I would like to share a small introductory course on programming with
gretl's scripting language, hansl. You can find the initial *five
lectures* available here, with more lectures to follow over the next
*2.5 months*.
https://github.com/gretl-project/hansl-coding
Additionally, the solution scripts for the exercises are located in the
"exercises" folder within the same repository. If you encounter any
errors or issues, please feel free to let me know by opening an issue on
GitHub.
This course is a side project of an actual introductory programming
lecture for business students that primarily uses Python. It's far from
being optimal, but still, I hope you find the materials helpful!
Best,
Artur
8 months
printf for string array
by Artur T.
Dear all,
I want to have a formatted printing of a string array:
<hansl>
strings S = defarray("A", "B", "C")
printf "My array: %s", S
</hansl>
This results in the error: "Data types not conformable for operation".
The help for the printf command says: "The format %s should be used for
strings." (last sentence in 1st paragraph). I guess that actually refers
to type "string". However, why shouldn't it work for an array of
strings, too?
Yes, I could (should?) make use of the flatten() function before
printing, but that does not feel natural (to me). Using the above code,
I would expect a line-by-line printout of the array items.
Sorry, I just recognize this E-Mail is a mixture of requesting help and
partially a kind of feature-request.
Best,
Artur
8 months
retirement of the gqtest contributed function package
by Sven Schreiber
Dear all,
the contributed but unmaintained function package "gqtest" is going to
be retired soon from the gretl package server.
The package implemented the old Goldfeld-Quandt test for heteroskedastic
residuals. However, nowadays this test is essentially irrelevant for
applied work --as also acknowledged in the package's help text--, the
standard recommendation would be to run something like the built-in
Breusch-Pagan test as a diagnostic.
(In scripting, you can do "modtest --breusch-pagan" with or without the
additional "--robust" switch. In the GUI in the window of your estimated
model, you would go to the menu Tests/Heteroscedasticity/Breusch-Pagan
or /Koenker. Of course, another option is to run White's test.)
Secondly, being unmaintained the package has had some technical issues
for quite some time now, and so the gretl team decided to retire it.
The package has been archived here:
https://github.com/gretl-project/gqtest. Of course, you can also keep a
local copy for yourself which will continue to work as always.
Thanks
Sven
8 months, 1 week
Question on package thres_infer
by Andreas Zervas
Hi all, especially Sven,
I was playing with the package thres_infer, and it appears that the threshold estimates from functions H_thresh_test() and H_thresh_estim() differ. Is it intented? Should they be the same? In the particular example from the sample script, which I pasted below, the values are similar, but I run it with data that give totally different results.
Any thought - suggestions?
Best regards,
Andreas
gretl version 2024d
Current session: 2025-04-08 16:37
# Sample script for thresh_infer
Read datafile C:\Program Files\gretl\data\misc\denmark.gdt
periodicity: 4, maxobs: 55
observations range: 1974:1 to 1987:3
Listing 5 variables:
0) const 1) LRM 2) LRY 3) IBO 4) IDE
Test of Null of No Threshold Against Alternative of Threshold
Under Maintained Assumption of Homoskedastic Errors
Number of Bootstrap Replications: 1000
Trimming percentage: 0.150000
Threshold Estimate: 0.088000
(46 % of obs in 1st regime)
LM-test for no threshold: 4.154898
Bootstrap p-value: 0.923000
*******************************************
Threshold regression based on Hansen (2000)
User choice: assume homoskedasticity
*******************************************
Global OLS Estimation, Without Threshold
Dependent Variable: mg
OLS Standard Errors Reported
coefficient std. error z p-value
-------------------------------------------------------
Constant 0.0705718 0.0272334 2.591 0.0096 ***
IBO -0.469693 0.229408 -2.047 0.0406 **
IDE 0.110332 0.500081 0.2206 0.8254
Observations = 54
Degrees of Freedom = 51
Sum of Squared Errors = 0.0487311
Residual Variance = 0.000955512
R-squared = 0.162774
Heterosked. test p-val = 0.365732
*************************************************************
Threshold Estimation, dependent variable: mg
Threshold Variable: IDE
Threshold Estimate = 0.074 90% CI: [0.074, 0.11]
Sum of Sq. Errors = 0.0435625 Residual Var. = 0.000907553
Joint R-squared = 0.252
Heterosked. test p-value: 0.225
*************************************************************
Regime 1: IDE <= 0.074000
(standard errors do not take into account threshold uncertainty)
coefficient std. error z p-value
-------------------------------------------------------
Constant -0.833454 0.386015 -2.159 0.0308 **
IBO -0.774593 0.915857 -0.8458 0.3977
IDE 13.4116 6.06844 2.210 0.0271 **
Observations = 5
Degrees of Freedom = 2
Sum of Squared Errors = 0.00612267
Residual Variance = 0.00306133
R-squared = 0.425631
Regime 2: IDE > 0.074000
(standard errors do not take into account threshold uncertainty)
coefficient std. error z p-value
-------------------------------------------------------
Constant 0.0727286 0.0303053 2.400 0.0164 **
IBO -0.487763 0.233237 -2.091 0.0365 **
IDE 0.116314 0.505722 0.2300 0.8181
Observations = 49
Degrees of Freedom = 46
Sum of Squared Errors = 0.0374399
Residual Variance = 0.000813911
R-squared = 0.178561
8 months, 2 weeks
