Fixed effects forecast
by Ricardo Gonçalves Silva
Hi,
Can Gretl forecast 1 to 3 periods ahead an estimated panel data(fixed-effects with no iterations) model?
HTH
RIck
13 years, 8 months
Paper advocating open source software and gretl
by Talha Yalta
Dear gretl users:
You might be interested to hear about my new paper entitled "Should
Economists Use Open Source Software for Doing Research?" published
this month in Computational Economics. The paper investigates
econometric software reliability and advocates the use of open source
software by taking gretl as a case study and showing how responsive
and transparent its development process is. I think many people here
might find it an interesting read.
More information and the download link is available here:
http://ideas.repec.org/a/kap/compec/v35y2010i4p371-394.html
I can send a working paper version if you do not have access to the above.
Cheers
A. Talha Yalta
--
“Remember not only to say the right thing in the right place, but far
more difficult still, to leave unsaid the wrong thing at the tempting
moment.” - Benjamin Franklin (1706-1790)
--
14 years, 1 month
Re: [Gretl-users] From daily to monthly or quaterly data...
by Giuseppe
Thanks a lot.
Giuseppe Vittucci
On Tue, 26 Oct 2010, Giuseppe Vittucci wrote:
> I searched the manual and the mailing list archive but I found no clue.
> I have a daily financial time series and I would like to "shrink" the db
> from a daily to a monthly frequency taking some statistics for each
> relevant period. E.g. the mean or the median of the daily prices for
> each month, etc.
> Is there a way in gretl to do this?
You want the "dataset" command:
dataset compact 12
will convert daily data to monthly. Summation and mean are
supported, but not the median at present.
Allin Cottrell
_______________________________________________
Gretl-users mailing list
Gretl-users(a)lists.wfu.edu
http://lists.wfu.edu/mailman/listinfo/gretl-users
14 years, 5 months
Re: [Gretl-users] Forecasting Future Trends with Gretl
by Allin Cottrell
On Sun, 31 Oct 2010, Anton Bletsov wrote:
> I am building an ARIMA model with Gretl, and I want to forecast the changes
> in the value of my dependent variable for the period 2010-2012, based on my
> previous observations. Although I added two extra observations (of course,
> there are no actual values for those), I keep getting this message when I
> try to make a forecast for the period:
>
> There are no observations available for forecasting
> out of sample. If you wish, you can add observations
> (Data menu, Edit data), or you can shorten the sample
> range over which the model is estimated (Sample menu).
Can you send me a copy of the dataset you're using, and the model
specification? From the information given, I can't say what's
happening here.
As a comparison, you might try this:
* Open the Ramanathan dataset data9-7.
* Under the Data menu, choose Add observations and select
2 additional observations
* Under the Model menu, select an ARMA(1,1) model for
the variable QNC
* Under the Analysis menu in the model window, select
Forecasts: you will find that you're offered a
dynamic forecast for the two extra observations.
This is the expected behavior.
Allin Cottrell
14 years, 5 months
Forecasting Future Trends with Gretl
by Anton Bletsov
Hello,
I am building an ARIMA model with Gretl, and I want to forecast the changes
in the value of my dependent variable for the period 2010-2012, based on my
previous observations. Although I added two extra observations (of course,
there are no actual values for those), I keep getting this message when I
try to make a forecast for the period:
There are no observations available for forecasting
out of sample. If you wish, you can add observations
(Data menu, Edit data), or you can shorten the sample
range over which the model is estimated (Sample menu).
What should I do in order to eliminate this problem?
Thank you in advance.
14 years, 5 months
Re: [Gretl-users] Gretl-users Digest, Vol 45, Issue 27
by Allin Cottrell
On Wed, 27 Oct 2010, [iso-8859-1] Gústaf Steingrímsson wrote:
> Maybe I was unclear about my problem. I was using standard
> non-seasonal ARIMA(1,1,1) model which should be on the form:
>
> Y^(t) = c + Y(t-1) + Phi*(Y(t-1)-Y(t-2)) + theta*e(t-1)
>
> I got parameters from Gretl for c, Phi and theta. I also got
> time series for Y(t) and Y^(t) for many values of t's.
Please see the discussion in the Gretl User's Guide, The "Time
series models" chapter, around equations (21.4) and (21.5) in
particular. There are various ways of formulating AR(I)MA
models, and you have to be aware which one gretl is using.
If you're using exact ML, then in the equation you give above,
you'll need to replace c with c*(1-phi). That should give you
something very close to what gretl computes automatically, if not
identical. There may also be a difference in the treatment of
initial values; I'll have to look into that.
Allin Cottrell
14 years, 5 months
Re: [Gretl-users] Gretl-users Digest, Vol 45, Issue 27
by Gústaf Steingrímsson
Hi and thanks for your reply
Maybe I was unclear about my problem. I was using standard non-seasonal ARIMA(1,1,1) model which should be on the form:
Y^(t) = c + Y(t-1) + Phi*(Y(t-1)-Y(t-2)) + theta*e(t-1)
I got parameters from Gretl for c, Phi and theta. I also got time series for Y(t) and Y^(t) for many values of t's.
I assumed that e(t-1) = Y(t) - Y^(t-1) in order to caluculate on compare values of Y^(t) that the model got and what I should get on the spreadsheet. The values didnt match at all. There seemed to be no systemic explanation for the difference between Y^(t) that the model got and what I got. It seemed to be purely random. I did this several times for various time series.
Best regards
Gustaf
-----Original Message-----
From: gretl-users-bounces(a)lists.wfu.edu [mailto:gretl-users-bounces@lists.wfu.edu] On Behalf Of gretl-users-request(a)lists.wfu.edu
Sent: 27. október 2010 16:00
To: gretl-users(a)lists.wfu.edu
Subject: Gretl-users Digest, Vol 45, Issue 27
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. Re: Simple ARIMA problem (Dr. Ioannis A. Venetis)
2. Re: HP-filter problem (Giuseppe)
3. Re: From daily to monthly or quaterly data... (Giuseppe)
4. Re: HP-filter problem (Eloy A. Fisher Hogan)
----------------------------------------------------------------------
Message: 1
Date: Wed, 27 Oct 2010 10:16:46 +0300
From: "Dr. Ioannis A. Venetis" <ivenetis(a)upatras.gr>
Subject: Re: [Gretl-users] Simple ARIMA problem
To: <gretl-users(a)lists.wfu.edu>
Message-ID: <F05A67EE71254F6C91B00A50B2CB7888@ivenetis>
Content-Type: text/plain; charset="iso-8859-7"
Dear Gustaf and Richard,
I guess part of the problem is the estimation method. GRETL offers Exact
maximum likelihood estimation (exact MLE) and conditional MLE for ARIMA
models. Only the second is equivalent to OLS. Exact and conditional ML
parameter estimates will "tend" to coincide only in "large" samples.
If you try OLS in another software and conditional MLE in GRETL you should
get the same parameter estimates and hence the same forecasts.
With respect to the spreadsheet experiment I cannot be sure what the problem
was? Are you 100% certain that you entered lags and lagged estimated
prediction errors appropriately in the spreadsheet?
Hope I helped a bit.
Yiannis
*******************************************************
*******************************************************
Dr Ioannis A. Venetis
Assistant Professor
University of Patras
Department of Economic Sciences
University Campus, Rio, 26504, Greece
Tel: +30 2610 969 964
*******************************************************
??????? ?. ???????
????????? ?????????
???????????? ??????
????? ??????????? ?????????
?????????????????, ???, 26504
???: 2610 969 964
*******************************************************
*******************************************************
-----?????? ??????-----
???: gretl-users-bounces(a)lists.wfu.edu
[mailto:gretl-users-bounces@lists.wfu.edu] ?? ?????? ???
gretl-users-request(a)lists.wfu.edu
????????: Wednesday, October 27, 2010 9:04 AM
????: gretl-users(a)lists.wfu.edu
????: Gretl-users Digest, Vol 45, 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. Re: HP-filter problem (Eloy A. Fisher Hogan)
2. Re: HP-filter problem (Allin Cottrell)
3. Simple ARIMA problem (G?staf Steingr?msson)
4. From daily to monthly or quaterly data... (Giuseppe Vittucci)
5. Re: From daily to monthly or quaterly data... (Allin Cottrell)
6. Re: Simple ARIMA problem (Dr RJF Hudson)
----------------------------------------------------------------------
Message: 1
Date: Wed, 27 Oct 2010 00:12:04 +0000
From: "Eloy A. Fisher Hogan" <eloyfisher(a)hotmail.com>
Subject: Re: [Gretl-users] HP-filter problem
To: <gretl-users(a)lists.wfu.edu>
Message-ID: <BLU111-W20553C09510BDB930E4D2FD3430(a)phx.gbl>
Content-Type: text/plain; charset="iso-8859-1"
Allin,
I think I have the latest GRETL for Linux from the Ubuntu repositories - or
is it?
Gretl 1.8.7
2010-02-04
Thanks Allin!
EF
PS. Btw, GRETL is great!
> Date: Mon, 25 Oct 2010 18:10:39 -0400
> From: cottrell(a)wfu.edu
> To: gretl-users(a)lists.wfu.edu
> Subject: Re: [Gretl-users] HP-filter problem
>
> On Mon, 25 Oct 2010, Eloy A. Fisher Hogan wrote:
>
> > I am running an HP filter in a script, but when I type:
> >
> > genr cyc_yt = hpfilt(yt, 6.25)
> > genr tre_yt=yt-cyc_yt
> >
> > I get:
> >
> > Expected ')' but found ','
> > Syntax error in command line
>
> What version of gretl are you running (under Help, About: version
> and build date)?
>
> The command you give above works OK here on current gretl.
>
> Allin Cottrell
>
> _______________________________________________
> Gretl-users mailing list
> Gretl-users(a)lists.wfu.edu
> http://lists.wfu.edu/mailman/listinfo/gretl-users
14 years, 5 months
Re: [Gretl-users] HP-filter problem
by Giuseppe
I use Ubuntu 10.04.
The debian package requires missing dependencies.
I compiled the program directly from the source.
Download the 9.1 version from:
http://prdownloads.sourceforge.net/gretl/gretl-1.9.1.tar.bz2
Unpack. Open a terminal and write:
cd [gretl_source_directory]
sudo apt-get build-dep gretl
./configure
make
sudo make install
That's all
Giuseppe Vittucci
On Tue, 2010-10-26 at 23:34 -0400, Allin Cottrell wrote:
> On Wed, 27 Oct 2010, Eloy A. Fisher Hogan wrote:
>
> > I think I have the latest GRETL for Linux from the Ubuntu
> > repositories - or is it?
> >
> > Gretl 1.8.7
>
> Ah, the change that allowed more than one argument to hpfilt came
> in with gretl 1.9.0, so that explains it. Version 1.9.1 has been
> available since June. You can get packages for 1.9.1 from Debian
> sid: http://packages.debian.org/sid/gretl , though I'm not sure if
> these will work OK with Ubuntu.
>
> Allin Cottrell
> _______________________________________________
> Gretl-users mailing list
> Gretl-users(a)lists.wfu.edu
> http://lists.wfu.edu/mailman/listinfo/gretl-users
14 years, 5 months
Re: [Gretl-users] Simple ARIMA problem
by Dr. Ioannis A. Venetis
Dear Gustaf and Richard,
I guess part of the problem is the estimation method. GRETL offers Exact
maximum likelihood estimation (exact MLE) and conditional MLE for ARIMA
models. Only the second is equivalent to OLS. Exact and conditional ML
parameter estimates will "tend" to coincide only in "large" samples.
If you try OLS in another software and conditional MLE in GRETL you should
get the same parameter estimates and hence the same forecasts.
With respect to the spreadsheet experiment I cannot be sure what the problem
was? Are you 100% certain that you entered lags and lagged estimated
prediction errors appropriately in the spreadsheet?
Hope I helped a bit.
Yiannis
*******************************************************
*******************************************************
Dr Ioannis A. Venetis
Assistant Professor
University of Patras
Department of Economic Sciences
University Campus, Rio, 26504, Greece
Tel: +30 2610 969 964
*******************************************************
Ιωάννης Α. Βενέτης
Επίκουρος Καθηγητής
Πανεπιστήμιο Πατρών
Τμήμα Οικονομικών Επιστημών
Πανεπιστημιούπολη, Ρίο, 26504
Τηλ: 2610 969 964
*******************************************************
*******************************************************
-----Αρχικό μήνυμα-----
Από: gretl-users-bounces(a)lists.wfu.edu
[mailto:gretl-users-bounces@lists.wfu.edu] εκ μέρους του
gretl-users-request(a)lists.wfu.edu
Αποστολή: Wednesday, October 27, 2010 9:04 AM
Προς: gretl-users(a)lists.wfu.edu
Θέμα: Gretl-users Digest, Vol 45, 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. Re: HP-filter problem (Eloy A. Fisher Hogan)
2. Re: HP-filter problem (Allin Cottrell)
3. Simple ARIMA problem (G?staf Steingr?msson)
4. From daily to monthly or quaterly data... (Giuseppe Vittucci)
5. Re: From daily to monthly or quaterly data... (Allin Cottrell)
6. Re: Simple ARIMA problem (Dr RJF Hudson)
----------------------------------------------------------------------
Message: 1
Date: Wed, 27 Oct 2010 00:12:04 +0000
From: "Eloy A. Fisher Hogan" <eloyfisher(a)hotmail.com>
Subject: Re: [Gretl-users] HP-filter problem
To: <gretl-users(a)lists.wfu.edu>
Message-ID: <BLU111-W20553C09510BDB930E4D2FD3430(a)phx.gbl>
Content-Type: text/plain; charset="iso-8859-1"
Allin,
I think I have the latest GRETL for Linux from the Ubuntu repositories - or
is it?
Gretl 1.8.7
2010-02-04
Thanks Allin!
EF
PS. Btw, GRETL is great!
> Date: Mon, 25 Oct 2010 18:10:39 -0400
> From: cottrell(a)wfu.edu
> To: gretl-users(a)lists.wfu.edu
> Subject: Re: [Gretl-users] HP-filter problem
>
> On Mon, 25 Oct 2010, Eloy A. Fisher Hogan wrote:
>
> > I am running an HP filter in a script, but when I type:
> >
> > genr cyc_yt = hpfilt(yt, 6.25)
> > genr tre_yt=yt-cyc_yt
> >
> > I get:
> >
> > Expected ')' but found ','
> > Syntax error in command line
>
> What version of gretl are you running (under Help, About: version
> and build date)?
>
> The command you give above works OK here on current gretl.
>
> Allin Cottrell
>
> _______________________________________________
> Gretl-users mailing list
> Gretl-users(a)lists.wfu.edu
> http://lists.wfu.edu/mailman/listinfo/gretl-users
14 years, 5 months
Simple ARIMA problem
by Gústaf Steingrímsson
Hi
While trying to work with ARIMA(1,1,1) in Gretl I got into problems. The problem is that having set upp the numbers (values, prediction and errors that was produced by Gretl) in spreadsheet and using the parameters that I got I couldnt get the same forecast number as Gretl got. I used just this simple formula to calculate the forecast:
[cid:image001.gif@01CB7516.F0E83070]
That is why I ask: Is this formula differently in ARIMA(1,1,1) as it is calculated by Gretl and how is that?
I also tried to use OLS on a time series y(t) which had been differenced one time (d(1)) and the explanatory variable was y(t-1) and got a different parameters result than using ARIMA(1,1,0) which I shouldn't or what?
I would be very thankful for useful replies.
Kveðja / With regards
Gústaf Steingrímsson
Landsbankinn
Sérfræðingur / Analyst
Áhættustýring / Risk Management
Sími / Tel.: (+354) 410 6993
Farsími / Mobile: (+354) 820 2646
Fax: (+354) 410 3010
www.landsbanki.is<http://www.landsbanki.is/>
Landsbankinn (NBI hf.), kt. 471008-0280, Austurstræti 11, 155 Reykjavík, er skráð hlutafélag og starfar samkvæmt heimild og undir eftirliti Fjármálaeftirlitsins.
Landsbankinn (NBI hf.), Austurstræti 11, 155 Reykjavík. is incorporated in Iceland with limited liability (Reg. No: 471008-0280) and is authorised and regulated by the Financial Supervisory Authority in Iceland (Fjármálaeftirlitið).
Fyrirvari/Disclaimer: http://www.landsbankinn.is/disclaimer
14 years, 5 months
