Working with models
by Frederic Beister
Hi,
I'm fairly new to gretl and intend to use it mainly as a tool to
faciliate my research. I'm a computer scientist and in no way an
econometrician. I'm currently looking into ARMA models and all
variations thereof (SARIMA, ARIMA, ...).
I'm trying to model time-series with ARMA models like this (on a big
computing machine because locally it might take too long)
m1 <- arima 1 1 1 ; 1 1 1 ; Pwr
Now I have a model stored as m1 - from the GUI I know that I can plot
several graphs such as residuals etc.. How do I do this with the CLI or
how can I "export" the model to my local machine so that I can use it there?
To export I already tried modeltab add / store with no success - "store"
only stores variables and modeltab results in "modeltab: command not
available". "gnuplot m1" or similar doesn't work either as m1 is not a
variable.
Thanks in advance and best regards
Frederic
--
Frederic Beister
University of Paderborn
Computer Networks Group
E-Mail: frederic.beister(a)uni-paderborn.de
Phone: +49 5251 / 60 - 5373
Web: http://wwwcs.upb.de/cs/ag-karl
Room O3.167
13 years, 3 months
Optimization
by clarodina＠lycos.com
Hi,
1) Doing a adf 0 y --ct --verbose, there is a time coefficient on the output
What is this time coefficient?
2) Does gretl allow doing regression with optimization of some condition?
Have 6 data D1 to D6
Want to regress D1 against D2 to D6
Do a adf on the $yhat and have t value
Want to have the coefficients of D2 to D6 MAXIMISING the t value
Try seraching the manual on the 2)
Claordina
13 years, 3 months
Up date
by Gilberto Matute A.
Estoy utilizando Gretl 1.9.1 paero me gustaria actualizarlo a 1.9.6.
¿Cómo puedo lograr esto?
Gracias por su ayuda.
13 years, 3 months
problem with a function: 'xy' is not a name of a variable
by artur tarassow
Hey gretl-community,
I've got a small problem with a function. Here is a small part of this
function:
---------------------------------------------------------
function void adfgls (int pmx[0::1] "lag order",
scalar crit "Critical value for initial OLS",
list vars "List of variables to test")
genr time
loop foreach i vars
ols $i const time $i(-1 to -pmx) --robust
omit --auto=crit
lis = $xlist
check = inlist(lis, time)
endloop
end function
open pe.gdt
scalar crit = 0.05
scalar px = 8
list X = pe price
adfgls(px, crit, X)
----------------------------------------------------------
I obtain the following error:
adfgls(px, crit, X)
'pe' is not the name of a variable
*** error in function adfgls
> ols $i const time $i(-1 to -pmx) --robust
What is wrong with the function?
Best,
Artur
13 years, 3 months
R:VAR parameters
by alexkakashi＠libero.it
Thanks for your answer. In my equations the restrictions are non-linear. For
example, can I use the following restriction
restrict varsys
> b[1,2]*b[2,2] = 0
>end restrict
Best regards.
Alessandro
>----Messaggio originale----
>Da: gretl-users-request(a)lists.wfu.edu
>Data: 14/12/2011 18.00
>A: <gretl-users(a)lists.wfu.edu>
>Ogg: Gretl-users Digest, Vol 59, Issue 17
>
>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: Different ols (Sven Schreiber)
> 2. VAR parameters (alexkakashi(a)libero.it)
> 3. Re: VAR parameters (Sven Schreiber)
> 4. Re: Gretl-users Digest, Vol 59, Issue 16 (Annaert Jan)
> 5. Re: VAR parameters (Allin Cottrell)
> 6. Re: Different ols (Allin Cottrell)
>
>
>----------------------------------------------------------------------
>
>Message: 1
>Date: Wed, 14 Dec 2011 08:38:06 +0100
>From: Sven Schreiber <svetosch(a)gmx.net>
>Subject: Re: [Gretl-users] Different ols
>To: gretl-users(a)lists.wfu.edu
>Message-ID: <4EE8525E.7030606(a)gmx.net>
>Content-Type: text/plain; charset=ISO-8859-1
>
>You forgot the constant.
>-sven
>
>On 12/14/2011 08:25 AM, clarodina(a)lycos.com wrote:
>> Allin Cottrell,
>>
>> The scatterplot with v1 on y axis and v2 on x axis gives y=17.9+0.0453x
>>
>> Using ols v1 v2 OR ols v2 v1 gives 0.181744 and 5.49601 coefficient
>> which is different
>> the scatterplot
>>
>> And the graph for selecting v1 against v2 fiitted vs obs is different
>> from the graph from the scatterplot
>>
>> Wanted to save the residual against v2 from the scatterplot and have the
>> value on the gretl
>> How to do using GUI rather the command?
>>
>> Clarodina
>>
>>
>> ? m6 <- ols v1 v2
>>
>> m6: OLS, using observations 1950-1954 (T = 5)
>> Dependent variable: v1
>>
>> coefficient std. error t-ratio p-value
>> --------------------------------------------------------
>> v2 0.181744 0.00306098 59.37 4.82e-07 ***
>>
>> Mean dependent var 23.84800 S.D. dependent var 0.313321
>> Sum squared resid 3.223300 S.E. of regression 0.897678
>> R-squared 0.998867 Adjusted R-squared 0.998867
>> F(1, 4) 3525.337 P-value(F) 4.82e-07
>> Log-likelihood -5.997112 Akaike criterion 13.99422
>> Schwarz criterion 13.60366 Hannan-Quinn 12.94599
>> rho 0.620803 Durbin-Watson 0.419277
>>
>> ? m6 <- ols v2 v1
>>
>> m6: OLS, using observations 1950-1954 (T = 5)
>> Dependent variable: v2
>>
>> coefficient std. error t-ratio p-value
>> --------------------------------------------------------
>> v1 5.49601 0.0925651 59.37 4.82e-07 ***
>>
>> Mean dependent var 131.0220 S.D. dependent var 6.532206
>> Sum squared resid 97.47384 S.E. of regression 4.936442
>> R-squared 0.998867 Adjusted R-squared 0.998867
>> F(1, 4) 3525.337 P-value(F) 4.82e-07
>> Log-likelihood -14.52006 Akaike criterion 31.04012
>> Schwarz criterion 30.64955 Hannan-Quinn 29.99189
>> rho 0.635889 Durbin-Watson 0.420088
>>
>>
>> _______________________________________________
>> Gretl-users mailing list
>> Gretl-users(a)lists.wfu.edu
>> http://lists.wfu.edu/mailman/listinfo/gretl-users
>
>
>
>------------------------------
>
>Message: 2
>Date: Wed, 14 Dec 2011 11:24:31 +0100 (CET)
>From: "alexkakashi(a)libero.it" <alexkakashi(a)libero.it>
>Subject: [Gretl-users] VAR parameters
>To: gretl-users(a)lists.wfu.edu
>Message-ID:
> <17122838.2794091323858271987.JavaMail.defaultUser@defaultHost>
>Content-Type: text/plain;charset="UTF-8"
>
>Hi,
>I have the following problem. I should estimate a VAR model in which some
>parameters are constrained. How can I restrict some coefficients equal to 0
in
>gretl?
>
>Best regards
>
>Alessandro
>
>
>------------------------------
>
>Message: 3
>Date: Wed, 14 Dec 2011 11:28:25 +0100
>From: Sven Schreiber <svetosch(a)gmx.net>
>Subject: Re: [Gretl-users] VAR parameters
>To: gretl-users(a)lists.wfu.edu
>Message-ID: <4EE87A49.8000807(a)gmx.net>
>Content-Type: text/plain; charset=ISO-8859-1
>
>On 12/14/2011 11:24 AM, alexkakashi(a)libero.it wrote:
>> Hi,
>> I have the following problem. I should estimate a VAR model in which some
>> parameters are constrained. How can I restrict some coefficients equal to 0
in
>> gretl?
>>
>
>set up a SUR system:
>
>system method=sur
> equation ...
> equation ...
> equation ...
> ....
>end system
>
>The equation specifying syntax is like for a normal equation.
>
>hth,
>sven
>
>
>------------------------------
>
>Message: 4
>Date: Wed, 14 Dec 2011 11:35:23 +0000
>From: Annaert Jan <jan.annaert(a)ua.ac.be>
>Subject: Re: [Gretl-users] Gretl-users Digest, Vol 59, Issue 16
>To: "gretl-users(a)lists.wfu.edu" <gretl-users(a)lists.wfu.edu>
>Message-ID:
> <F194DC2C2D2F4140AC6D295D5AA1F3CB7A789C04(a)xmail31.ad.ua.ac.be>
>Content-Type: text/plain; charset="us-ascii"
>
>Don't forget to add the constant in the regression!
>
>Jan
>
>
>-----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: woensdag 14 december 2011 8:26
>To: gretl-users(a)lists.wfu.edu
>Subject: Gretl-users Digest, Vol 59, Issue 16
>
>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..."
>
>
>
>------------------------------
>
>Message: 5
>Date: Wed, 14 Dec 2011 10:28:55 -0500 (EST)
>From: Allin Cottrell <cottrell(a)wfu.edu>
>Subject: Re: [Gretl-users] VAR parameters
>To: Gretl list <gretl-users(a)lists.wfu.edu>
>Message-ID: <alpine.LNX.2.00.1112141013340.455(a)waverley.dhcp.wfu.edu>
>Content-Type: TEXT/PLAIN; charset=US-ASCII; format=flowed
>
>On Wed, 14 Dec 2011, Sven Schreiber wrote:
>
>> On 12/14/2011 11:24 AM, alexkakashi(a)libero.it wrote:
>>> Hi,
>>> I have the following problem. I should estimate a VAR model in which some
>>> parameters are constrained. How can I restrict some coefficients equal to
0 in
>>> gretl?
>>
>> set up a SUR system:
>>
>> system method=sur
>> equation ...
>> equation ...
>> equation ...
>> ....
>> end system
>>
>> The equation specifying syntax is like for a normal equation.
>
>We should probably enable the "restrict" command for VARs at
>some point, but as Sven says you can do this as an SUR system.
>Here's a trivial example:
>
><hansl>
>open data9-7
>
># set up the common regressors
>list X = const INCOME(-1 to -4) PRIME(-1 to -4)
>varsys <- system
> equation INCOME X
> equation PRIME X
>end system
>
>restrict varsys
> b[1,2] - b[2,2] = 0
>end restrict
>
>estimate varsys method=SUR
></hansl>
>
>Allin Cottrell
>
>
>------------------------------
>
>Message: 6
>Date: Wed, 14 Dec 2011 10:37:44 -0500 (EST)
>From: Allin Cottrell <cottrell(a)wfu.edu>
>Subject: Re: [Gretl-users] Different ols
>To: Gretl list <gretl-users(a)lists.wfu.edu>
>Message-ID: <alpine.LNX.2.00.1112141034110.455(a)waverley.dhcp.wfu.edu>
>Content-Type: TEXT/PLAIN; charset=US-ASCII; format=flowed
>
>On Wed, 14 Dec 2011, clarodina(a)lycos.com wrote:
>
>[ nothing readable other than attached HTML ]
>
>Please do not send HTML mail to the gretl list.
>
>But in relation to "Wanted to save the residual against v2
>from the scatterplot and have the value on the gretl How to do
>using GUI rather the command?":
>
>Use the Save menu in the model window.
>
>--
>Allin Cottrell
>Department of Economics
>Wake Forest University, NC
>
>
>
>------------------------------
>
>_______________________________________________
>Gretl-users mailing list
>Gretl-users(a)lists.wfu.edu
>http://lists.wfu.edu/mailman/listinfo/gretl-users
>
>End of Gretl-users Digest, Vol 59, Issue 17
>*******************************************
>
13 years, 3 months
