Re: [Gretl-users] 1.9.4 source not found!
by Allin Cottrell

On Thu, 24 Feb 2011, Bob McCall wrote:
> The Gretl page has a link to gretl-1.9.4.tar.bz2 but the link takes you to a
> windows download
> for 1.9.3.
> What is the latest source version available (not cvs) ?
Oops, that must have been a typo when I was updating some html
docs. But as it happens gretl 1.9.4 is just in the release process
and will be on the site very shortly.
Allin Cottrell
13 years, 7 months

Re: [Gretl-users] 1.9.4 source not found!
by Allin Cottrell

On Thu, 24 Feb 2011, Allin Cottrell wrote:
> On Thu, 24 Feb 2011, Bob McCall wrote:
>
> > The Gretl page has a link to gretl-1.9.4.tar.bz2 but the link takes you to a
> > windows download
> > for 1.9.3.
> > What is the latest source version available (not cvs) ?
>
> Oops, that must have been a typo when I was updating some html
> docs. But as it happens gretl 1.9.4 is just in the release process
> and will be on the site very shortly.
It's now there.
Allin Cottrell
13 years, 7 months

1.9.4 source not found!
by Bob McCall

The Gretl page has a link to gretl-1.9.4.tar.bz2 but the link takes you to a
windows download
for 1.9.3.
What is the latest source version available (not cvs) ?
thanks,
Bob
13 years, 7 months

Re: [Gretl-users] Bug in Test statistic calculator for the variance
by Allin Cottrell

On Sat, 19 Feb 2011, Leon Unger wrote:
> I found a (small) bug in the test statistic calculator (performed vie
> the GUI) [...]
(The distribution graph fails for the one-variance test, plus an
invalid p-value is given when the sample variance equals the
variance according to H0.)
Thanks, that's now fixed in CVS and snapshots.
Allin Cottrell
13 years, 7 months

Bug in Test statistic calculator for the variance
by Leon Unger

Hi there,
I found a (small) bug in the test statistic calculator (performed vie
the GUI):
I did the following test on the variance and after 'OK' an error window
came up:
Error: gnuplot command failed
and the output is:
Null hypothesis: population
variance = 2
Sample size: n = 200
Sample variance = 2
Test statistic: chi-square(199)
= 199 * 2/2 = 199
Two-tailed p-value = *1.027
* (one-tailed = 0.5133)
So, no graph and a p-Value bigger than one.
I'm using the snapshop of gretl with Windows 7.
Best
Pindar
13 years, 7 months

Estimation of a GARCH process with conditional skewness and kurtosis
by Johannes Lips

Hi,
I am trying to implement a GARCH method which explicitely models the
kurtosis and skewness.
A short summary could be found here:
http://hannes.fedorapeople.org/leon2005.pdf
What I got so far is the following:
open /usr/share/gretl/data/misc/djclose.gdt
series y=100*ldiff(djclose)
scalar mu=0.0
scalar beta0=1
scalar beta1=0.4
scalar beta2=0.0
scalar beta3=0.0
scalar gamma0=0.0
scalar gamma1=0.0
scalar gamma2=0.0
scalar delta0=0.0
scalar delta1=0.0
scalar delta2=0.0
mle ll= -0.5*(log(h) - 0.5*(eta)^2 +
log(1+(sk/6)*(eta^3-3*eta)+((ku-3)/24)*(eta^4-6*eta^2+3))^2-log(1+((sk^2)/6)+(ku-3)^2/24))
series e=y-mu
series h=var(y)
series eta=e/sqrt(abs(h))
series sk = (((y - mu)^3) / nobs(y))/ sd(y)^3
series ku = ((((y - mu)^4) / nobs(y))/ sd(y)^4) - 3
series h= beta0+beta1*(e(-1)+ beta3*sqrt(h(-1)))^2+beta2*h(-1)
series sk=gamma0 + gamma1*(eta(-1))^3 + gamma2*sk(-1)
series ku=delta0 + delta1*(eta(-1))^4 + delta2*ku(-1)
params mu beta0 beta1 beta2 beta3 gamma0 gamma1 gamma2 delta0 delta1 delta2
end mle
Not sure if everything is right because the execution fails with the
message 'Missing values encountered'.
I don't really know what's wrong or if my approach is correct.
Thanks for any help!
13 years, 7 months

Time Varying Parameters Model
by Henrique Andrade

Dear Gretl Community,
I trying to estimate a time-varying parameter model (TVP) using the Kalman
filter but I'm getting no success :( The model is a TVP Phillips curve for
Brazilian inflation augmented with the trade openness (my sample has 103
observations):
inf_f = b1(t)*inf(-1) + b2(t)*exp12m + b3(t)*gap(-1) + b4(t)*trade(-1) +
w(t)
b1(t) = b1(t-1) + v1(t)
b2(t) = b2(t-1) + v2(t)
b3(t) = b3(t-1) + v3(t)
b4(t) = b4(t-1) + v4(t)
Where:
inf_f - non monitored prices
exp12m - 12 month expected inflation
gap - output gap
trade - trade openness
Based upon equations (26.1) and (26.2) from the Gretl User's Guide (p. 216)
I'm trying to setup the filter. Please take a look at the following
commands:
list regressors = inf exp12m gap trade
matrix y = {inf_f} # Matrix order:(Txn)=(103x1)
matrix H = *?* # Matrix order:(rxn)=(4x1)
matrix x = {regressors} # Matrix order:(Txk)=(103x4)
matrix F = I(4) # Matrix order:(rxr)=(4x4)
matrix Q = *?* # Matrix order:(rxr)=(4x4)
How can I define H and Q?
Best,
--
*Henrique C. de Andrade*
Doutorando em Economia Aplicada
Universidade Federal do Rio Grande do Sul
www.ufrgs.br/ppge
13 years, 7 months

var in differences
by Remigijus Lapinskas

Dear All,
I have a VAR model in differences. How can I forecast levels in gretl?
Best regards,
Remigijus
13 years, 7 months

Time varying Kalman filter
by Ivan.Petrov＠mecglobal.com

Hi,
I'm trying to estimate parameters in the model:
y_t = y_{t-1}*u_{t}*lambda+N(0,sigma^2)
using Kalman filter. Where u{t} is t-th coordinate of the vector gathered
from my data.
I use next space state model:
eps_{t+1} = u{t} * lamba*eps_t + N(0,sigma^2)
y_t = 1 * eps_t + N (0, sigma2^2)
I wrote the script to estimate parameters using mle, but it alway gives
errors because mle can't find my vector U:
function void modify_F (matrix *F, scalar lambda, series *u, scalar t)
F[1,1]=lambda*u[t+1]
end function
kalman
obsy y
obsymat H
obsvar R
statemat F; modify_F(&F, lambda, &u, $kalman_t)
statevar Q
end kalman
mle logl = ERR ? NA : $kalman_llt
Q[1,1]=sigma^2
R[1,1]=sigma1^2
ERR=kfilter()
params sigma, lambda, sigma1
end mle --verbose --lbfgs
Is there any way how can I solve this problem?
Thanks,
Petrov Ivan
Privileged/Confidential Information may be contained in this message. If you
are not the addressee indicated in this message (or responsible for delivery
of the message to such person), you may not copy or deliver this message to
anyone. In such case, you should destroy this message and kindly notify the
sender by reply email. Please advise immediately if you or your employer
does not consent to email for messages of this kind. Opinions, conclusions
and other information in this message that do not relate to the official
business of the GroupM companies shall be understood as neither given nor
endorsed by it. GroupM companies are a member of WPP plc. For more
information on our business ethical standards and Corporate Responsibility
policies please refer to our website at
http://www.wpp.com/WPP/About/
13 years, 7 months

Re: [Gretl-users] error message
by Allin Cottrell

On Mon, 14 Feb 2011, Data Analytics Corp. wrote:
> I teach an econometrics course at Rutgers and use Gretl for lab
> assignments. One student is having a problem. He created a data set in
> Gretl but when he tried to plot two series (real GDP and the S&P500), he
> got this error message:
>
> "D:\gretl\wgnuplot.exe"
> "C:\Users\Cem's\AppData\Roaming\gretl\gpttmp.f06928": exit code 1"
As Helio said, the problem is probably with the apostrophe in the
path. But I thought we'd fixed that some time ago. What version of
gretl is the student running?
Allin Cottrell
13 years, 7 months