Gretlwiki announcement
by DeFeroci
Dear all,
I would like to announce that the gretl wiki is back up and running at:
https://gretlwiki.econ.univpm.it/index.php/Main_Page
For security reasons (and previous experience) only registered users can
modify the wiki and self-registration is no longer possible. So, if you
want to be added, please write to me privately or reply to this email.
Information on how to be registered and using the wiki can be found here:
https://gretlwiki.econ.univpm.it/index.php/Wiki
At the moment the wiki administrators are me and Cristián Arturo Ducoing
Ruiz.
If you have any suggestions or requests, you are welcome to contact us.
Happy holidays.
Federico
1 month
Simulated maximum likelihood using Halton numbers
by Alecos Papadopoulos
I have a sample of size n=1789. I need to run simulated maximum
likelihood on it, generating series of pairs of independent (w,u) per
observation to compute the value of the likelihood as an simuluated average.
Instead of using the RNG of gretl, I was thinking of using Halton
numbers, in sequences of length, say, 100. It would appear that this
requires to construct (once), 1789 (x) 2 = 3578 sequences of Halton
numbers of length 100.
Given my current understanding of the "halton" function in gretl, It
appears that I can only construct 40 distinct sequences maximum.
Naively, one could think "then, construct 40 sequences each of length
9000" and then chop them in pieces of length 100 to get the number of
required distinct sequences (or generate 1 sequence with length 357800
for that matter)... but how would one preserve the "well-balanced
spacing" in (0,1) that is the advantage of Halton numbers? (again this
"idea" is just to make small talk -it may be totally silly).
Is there any way to generate what I need inside gretl?
--
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
1 month, 1 week
Fwd: Norm of gradient in mle command
by Riccardo (Jack) Lucchetti
On 27/10/2023 01:16, Alecos Papadopoulos wrote:
> In an mle command with numerical derivatives I get in the script output
> (actual example)
>
> <<
>
> Gradients: 2.4007 6.7772 -5.3557 -0.89559 (norm
> 1.96e+000)
>
> >>
>
> Can somebody please advise which norm is this, preferably giving also
> its computation formula?
Call b is the parameter vector ad g the gradient vector, both with n
elements. Then the norm is computed as
gradnorm = sqrt(abs(b'g)/n)
I don't remember where this formula came from, Allin and I worked on
this piece of code long ago.
If you're curious to see the rest of the code, see
https://sourceforge.net/p/gretl/git/ci/master/tree/lib/src/gretl_bfgs.c
from line 1147 onwards.
-------------------------------------------------------
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
-------------------------------------------------------
--
-------------------------------------------------------
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
-------------------------------------------------------
1 month, 1 week
Fwd: Inconsistency in info related to Gauss-Legendre
by Riccardo (Jack) Lucchetti
On 27/10/2023 01:36, Alecos Papadopoulos wrote:
> In the help text for function "quadtable" we read
>
> <<When the Gauss–Legendre type is selected, the optional arguments a and
> b can be used to control the lower and upper limits of integration, the
> default values being –1 and 1. >>
>
> In Gretl guide ch. 37.4 page 384, in a table summarizing numerical
> integration we read
>
> <<Gauss–Legendre by default, a = 0 and b = 1>>
>
> Which one is the actual default value, a=-1, or a=0?
The guide is wrong, I'll correct it in a few minutes: the default is -1.
The pertinent code is at
https://sourceforge.net/p/gretl/git/ci/master/tree/lib/src/matrix_extra.c
line 2866.
Thanks!!!
-------------------------------------------------------
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
-------------------------------------------------------
--
-------------------------------------------------------
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
-------------------------------------------------------
1 month, 2 weeks
Inconsistency in info related to Gauss-Legendre
by Alecos Papadopoulos
In the help text for function "quadtable" we read
<<When the Gauss–Legendre type is selected, the optional arguments a and
b can be used to control the lower and upper limits of integration, the
default values being –1 and 1. >>
In Gretl guide ch. 37.4 page 384, in a table summarizing numerical
integration we read
<<Gauss–Legendre by default, a = 0 and b = 1>>
Which one is the actual default value, a=-1, or a=0?
Thanks.
--
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
1 month, 2 weeks
Norm of gradient in mle command
by Alecos Papadopoulos
In an mle command with numerical derivatives I get in the script output
(actual example)
<<
Gradients: 2.4007 6.7772 -5.3557 -0.89559 (norm
1.96e+000)
>>
Can somebody please advise which norm is this, preferably giving also
its computation formula?
Thanks.
--
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
1 month, 2 weeks
Gretl Crash on Windows
by Federico Fiorani
Hi everybody,
the following script crashes on Windows (gretl 2023c-git build date
2023-10-07) when I try to convert to a bundle.
<code>
bundle bun = null
bun.header = "text/html,application/xhtml+xml,application/xml"
bun.URL = "http://dataservices.imf.org/REST/SDMX_JSON.svc/Dataflow"
curl(&bun)
a = bread(bun.output)
</code>
Does anyone have the same problem?
Best
Federico
1 month, 3 weeks
panel regression HAC
by Alison Loddick
Hi,
If we have time series data, we can use HAC robust standard errors; however, with panel regression, the robust standard errors are Arellano or PCSE. Is there a way using programming that we can do HAC for panel regression? From what I have read, Arellano isn't as good at dealing with serial correlation. Although I'm aware we can do dynamic panel regression, I'm fighting with lecturers who want students to use Eviews because you can use HAC for panel regression there.
Thank you
Alison
Alison Loddick
BSc MSc PGCE CStat
Learning Development Tutor (Mathematics and Statistics)
Library and Learning Services
DDI +44 (0)1604 893502
[https://static.hobsons.co.uk/northampton/usermedia/Staff%20News/2017/New%...]
northampton.ac.uk
University of Northampton, Waterside Campus,
University Road, Northampton, NN1 5PH United Kingdom
University of Northampton: Transforming Lives and Inspiring Change www.northampton.ac.uk This e-mail is private and may be confidential and is for the intended recipient only. If you are not the intended recipient you are strictly prohibited from using, printing, copying, distributing or disseminating this e-mail or any information contained in it. We virus scan all E-mails leaving The University of Northampton but no warranty is given that this E-mail and any attachments are virus free. You should undertake your own virus checking. The right to monitor E-mail communications through our networks is reserved by us.
Disclaimer
The information contained in this communication from the sender is confidential. It is intended solely for use by the recipient and others authorized to receive it. If you are not the recipient, you are hereby notified that any disclosure, copying, distribution or taking action in relation of the contents of this information is strictly prohibited and may be unlawful.
This email has been scanned for viruses and malware, and may have been automatically archived by Mimecast, a leader in email security and cyber resilience. Mimecast integrates email defenses with brand protection, security awareness training, web security, compliance and other essential capabilities. Mimecast helps protect large and small organizations from malicious activity, human error and technology failure; and to lead the movement toward building a more resilient world. To find out more, visit our website.
2 months