request for feature
by John Paravantis
Any chances the development team adds zero-inflated Poisson and negative
binomial regression models (for count data) to gretl?
I have seen the zero-inflated Poisson example implemented with code in the
manual, but was hoping these two count data models could be added natively.
Many thanks for this wonderful program; after all these years, I am still
amazed it is offered for free.
John A. Paravantis
Associate Professor
University of Piraeus
Greece
6 years, 1 month
Re: [Gretl-users] Gretl-users Digest, Vol 145, Issue 26
by Raul Gimeno
Thank you for the answers!
Would it be possible to improve the manual to explain how to retrieve the
constant from the ARIMA estimation?
I am still struggling to get a simple AR estimation with the gretl menu.
The help does not help me further.
AR(1) process x(t) = 5 + 0.4x(t-1) + e with e ~N(0,1)
I've been using the new time series x* = x-mean = x-8.36 for the
estimation, with unconditional mean = 8.36
I am using the gretl menu Model/Times Series for the estimation (no script)
Estimation without a constant: phi_1 = 0.408
Estimation with a constant: const = -0.0135 and phi_1 = 0.4
Why is it not possible to get directly the estimated value for the constant
(5) in the estimation output?
How can I retrieve the estimated constant?
When should I use the option "include a constant"?
There is the possibility to use "specific lags" in the menu. When should I
use it?
When estimating an AR(2) I get :
phi_1 = 0.43 and phi_2 = -0.056
How do I know that the estimated AR(2) is not better than the estimated
AR(1)?
Thank you for your help
Raul
-----Ursprüngliche Nachricht-----
Von: gretl-users-bounces(a)lists.wfu.edu
[mailto:gretl-users-bounces@lists.wfu.edu] Im Auftrag von
gretl-users-request(a)lists.wfu.edu
Gesendet: Samstag, 23. Februar 2019 14:31
An: gretl-users(a)lists.wfu.edu
Betreff: Gretl-users Digest, Vol 145, Issue 26
Send Gretl-users mailing list submissions to
gretl-users(a)lists.wfu.edu
To subscribe or unsubscribe via the World Wide Web, visit
http://lists.wfu.edu/mailman/listinfo/gretl-users
or, via email, send a message with subject or body 'help' to
gretl-users-request(a)lists.wfu.edu
You can reach the person managing the list at
gretl-users-owner(a)lists.wfu.edu
When replying, please edit your Subject line so it is more specific than
"Re: Contents of Gretl-users digest..."
Today's Topics:
1. AR processes (Raul Gimeno)
2. Re: AR processes (Riccardo (Jack) Lucchetti)
3. Re: AR processes (Matteo Pelagatti)
4. Re: AR processes (Sven Schreiber)
----------------------------------------------------------------------
Message: 1
Date: Sat, 23 Feb 2019 10:48:45 +0100
From: "Raul Gimeno" <mrexito(a)vtxmail.ch>
To: <gretl-users(a)lists.wfu.edu>
Subject: [Gretl-users] AR processes
Message-ID: <003001d4cb5c$f847ecc0$e8d7c640$(a)vtxmail.ch>
Content-Type: text/plain; charset="us-ascii"
Hello
I simulated the following AR(1) process xt = 5 + 0.4xt-1 + e with e =
N(0,1) 200 observations
Estimation with OLS: xt = 5.047xt + 0.414xt-1
Estimation with gretl ARIMA: xt = 8.57 + 0.43xt-1
I simulated this AR(2) process: xt = 5 + 0.4xt-1 -0.1xt-2 + e
OLS estimation: xt = 4.64 + 0.377x t-1 -0.0075 x t-2
ARIMA estimation: xt = 7.36 + 0.369xt-1 -0.0076xt-2
Why is gretl giving such a bad estimation compared to OLS-estimation?
Thank you
Raul
6 years, 1 month
INFO: The GPlotFun package
by Artur T.
Dear all,
a while ago I've started to write a package merging different types of
plots which I collected during the past couple of years and frequently
used. This has resulted in the GPlotFun package centralizing all this stuff.
You can find the project here:
https://github.com/atecon/GPlotFun/tree/feature/progess
The current manual is here:
https://github.com/atecon/GPlotFun/blob/feature/progess/GPlotFun.pdf
I've just finished version 0.1 which should be seen as a sketch of an
idea for programming a flexible plotting library which may offer some
types of plots which are (currently?) not natively shipped with gretl.
There are still some bugs in the code and it is far from being complete
--- that's why I hesitate to upload it to the gretl server. Rather, I am
seeking to get some response and suggestions from the community.
Furthermore, I would be interested in collaborating with people as this
project is quite time-consuming.
I am also sure that each of you has some code snippets on interesting
plots which may be included into the package.
Let me know what you think about it.
Best,
Artur
6 years, 1 month
AR processes
by Raul Gimeno
Hello
I simulated the following AR(1) process xt = 5 + 0.4xt-1 + e with e =
N(0,1) 200 observations
Estimation with OLS: xt = 5.047xt + 0.414xt-1
Estimation with gretl ARIMA: xt = 8.57 + 0.43xt-1
I simulated this AR(2) process: xt = 5 + 0.4xt-1 -0.1xt-2 + e
OLS estimation: xt = 4.64 + 0.377x t-1 -0.0075 x t-2
ARIMA estimation: xt = 7.36 + 0.369xt-1 -0.0076xt-2
Why is gretl giving such a bad estimation compared to OLS-estimation?
Thank you
Raul
6 years, 1 month
Using 'fcast' for panel data
by Artur T.
Dear all,
I am trying to do some forecasting exercise using a panel data set. I am
a bit puzzled as the fcast command does not behave as I would have
thought. However, I am not sure I am using fcast correctly in this
example -- the manual doesn't include anything on the fcast command in
connection with panel data currently. Please, see the sample script below.
Best,
Artur
<hansl>
clear
set verbose off
open abdata.gdt -q
# Set training set
smpl time<=7 --restrict
# Estimate a model
list reg = const CAP WAGE
ols INDOUTPT reg --quiet
# Forecast out-of-sample
#-----------------------
# These options don't work
catch fcast --out-of-sample
catch fcast 1:8 140:9 --out-of-sample
catch fcast 1:8 140:9 --static
# In-sample fit: works
# fcast --static
# Forecast of the 8th and 9th entry only
fcast 8 9 --static
# Set test set manually
smpl time>7 --restrict --replace
# FIXME: By the way, note that the selected sample
# shown is "1:1 - 140:2" instead of "1:8 - 140:9"
# call fcast: RESULTS IN ERROR
catch fcast --out-of-sample # --> doesn't work
catch fcast --static # --> doesn't work
</hansl>
6 years, 1 month
issues with working on non-ASCII strings
by Fred Engst
Hi Allin and all,
I know you guys are very busy and I don’t want to bother you with every question that I have.
I looked into gretl documentations and searched in the email archive on this issue and can’t seems to find an answer for this.
Here is a little test script and output:
---------------------------------------------------------
gretl version 2019a-git
Current session: 2019-02-13 10:26
# assign unicode text
? string teststring = "ΑΒΓΔ"
Replaced string teststring
? string test = teststring[1]
Replaced string test
? print test
Α
? string teststring[1] = "Γ"
Error executing script: halting
> string teststring[1] = "Γ"
------------------------------------------------------------
two issues:
1.Those non-ascii character were pasted onto the scrip, for I can’t even enter them directly.
2. It seems that gretl handles the non-ascii character fine internally, but not on a scrip.
Anyway to work around this?
p.s. I’m not even sure the email that you see will show the right characters. Those are the first 4 characters of the Greek code page, i.e. UTF-8 CE91, CE92, CE93, & CE94.
Fred
6 years, 1 month
gretl crashed while searching for file within GUI
by Fred Engst
>> gretl crashed once again, but for a different reason this time.
>>
>> It seems that whenever I tried to do a search for files within GUI
>> after ?file->Open data->User file...? or ?file->Session
>> files->Open session??, it crashes right after it showed a list of
>> files.
>>
>> I can?t remember a time when I did a search like this without
>> gretl crashing.
>>
>> I suspect it has something to do with my character encoding. Even
>> though I use standard English, I have Chinese on my system also.
>>
>> This is more like a FYI, and it is not urgent, as I know how to
>> get around it easily.
>>
>> Attached is the crash report if it helps.
>
> Thanks, I've looked into this, but I'm still stumped.
>
> Taking my cue from your "I have Chinese on my system also" I created
> a Desktop directory with Chinese characters in its name, and put in
> there a gretl data file with Chinese characters in its name -- on a
> Macbook Air running OS X 10.10.5. Then I tried opening the data file
> in question via "/File/Open data/User file..." And the file opened
> without any problem.
>
> This was using gretl 2019a, but I can't think of anything remotely
> relevant that could have changed in quite a while.
>
> If you're able to give us any more information about the exact
> context of, or sequence of events leading up to, the crash, please
> do!
>
> You're running OS X 10.11.6, higher (though not far off) the version
> I'm on: maybe there're a relevant difference in that respect. I'll
> see if I can try the experiment on newer OS X.
>
> Allin
Hi Allin,
Thanks for trying.
I’m not sure why gretl keeps crashing on my Mac when I do a search within gretl. I tried log onto my administrative account and it crashes just the same. I tried to invoke an earlier version of gretl (1.9.11) but failed to make it work, after I have downloaded and installed GTK and XQuartz.
I then installed instead version 2016d which I have and it crashes just the same.
Since my os has a lot of quirky behaviours, lets not worry too much about my crash unless others report the same.
Fred
6 years, 1 month
Fixed Effect crashed when I tried to include over 5000 entity dummies
by Fred Engst
Hi guys,
I love gretl, but I have a problem.
When I run the builtin fixed effect model on a panel data with over 5000 firms, the gretl does fine.
But since the dependent variable has over 90% zeros, I tried to do a Tobit model with entity dummies (i.e. fixed effect tobit). Once I included over 5000 dummies using the gretl's GUI, gretl crashed with an error from the crash report: "Application Specific Information: detected buffer overflow”.
I then ran a fixed effect tobit by gretlcli from the command line and it gets stuck for 3 days without much progress.
Just now I tried to run a fixed effect by including entity dummies on OLS through GUI, it crashed gretl once again, with the same crash report.
Next, I tried fixed effect by including du_* on the OLS command through gretlcli, it was able to complete in a few minutes, much longer than the builtin panel model with the —fixed-effects option.
I’m a bit puzzled, however. If a panel fixed effect works fine, why can’t it work for a tobit model? Or it just will take a very long time to complete due to the nonlinearity?
Is there a way to do the fixed effect like the builtin panel way rather than the explicit including dummies way on a tobit model?
In either case, the buffer overflow should be looked at.
Thanks in advance for all your help.
Fred
6 years, 1 month
Is this genuine?
by John C Frain
I have received the message below which has subject "confirm
b200b8d63e83c1e1858c345eea3f664c173db200". AS I have not sent any
messages to this list for a while I was surprised at the excessive
bounces. I am always reluctant to reply to messages of this nature without
checking that the request is genuine.
Your membership in the mailing list Gretl-users has been disabled due
to excessive bounces The last bounce received from you was dated
12-Feb-2019. You will not get any more messages from this list until
you re-enable your membership. You will receive 3 more reminders like
this before your membership in the list is deleted.
To re-enable your membership, you can simply respond to this message
(leaving the Subject: line intact)
etc. etc.
John C Frain
3 Aranleigh Park
Rathfarnham
Dublin 14
Ireland
www.tcd.ie/Economics/staff/frainj/home.html
mailto:frainj@tcd.ie
mailto:frainj@gmail.com
6 years, 1 month
Re: [Gretl-users] Gretl-users Digest, Vol 145, Issue 16
by Fred Engst
>
> Message: 4
> Date: Mon, 11 Feb 2019 19:42:17 -0500 (EST)
> From: Allin Cottrell <cottrell(a)wfu.edu>
> To: Gretl list <gretl-users(a)lists.wfu.edu>
> Subject: Re: [Gretl-users] Fixed Effect crashed when I tried to
> include over 5000 entity dummies
> Message-ID: <alpine.LFD.2.20.3.1902111935360.3472(a)myrtle.attlocal.net>
> Content-Type: text/plain; charset=US-ASCII; format=flowed
>
> On Sun, 10 Feb 2019, Fred Engst wrote:
>
>> here is the top part of my crash report [...]
>
> Thanks. If we're ever to get to the bottom of what happened here, a
> little more information could be helpful, namely
>
> * What was the time-series length of your panel?
> * How many regressors did you have, besides the 5000
> dummies?
> * Roughly how long did the estimation run before the crash?
> * Was there any evidence that estimation was finished at the
> time, or was it still struggling away?
>
> Also, if you'd like to send me the full crash report offlist, maybe
> I'll find something useful in it.
>
> Allin
>
Thanks Allin for getting back to me.
You guys are doing a great job creating gretl.
Here is a part of the output from running a script from gretlcli that did not crash:
-------------------------------------------------------------------------------------------------
periodicity: 3, maxobs: 15750
observations range: 1:1 to 5250:3
Listing 13 variables:
0) const 1) company 2) year
3) l_NPV 4) l_total_asset 5) l_fixed_capital
6) l_longterm_debt 7) l_floating_debt 8) l_govern_capital
9) l_adfee 10) l_rdfee 11) l_salary
12) flognpv
? genr unitdum
Panel dummy variables generated.
? genr timedum
Panel dummy variables generated.
? ols l_NPV 0 l_total_asset l_fixed_capital l_longterm_debt \
l_floating_debt l_govern_capital l_adfee l_rdfee l_salary dt_* du_*
------------------------------------------------------------------------------------------------------
When I use OLS on the GUI, once I add those unit dummies and click OK, it will crash right away.
Attached is the crash report using OLS, not the one using tobit.
The crash report has 5 lines on gretl:
7 gretl 0x000000010eb7a4ba lib_command_sprintf + 186
8 gretl 0x000000010eb826b7 do_model + 359
9 gretl 0x000000010ebaf5a0 selector_doit + 64
31 gretl 0x000000010eb5e4a7 main + 3847
32 gretl 0x000000010eafc974 start + 52
Fred
6 years, 1 month
