Examples of Gretl scripts
by Carlos Andrade

Dear All,
Where to get examples of Gretl scripts for different types of analysis?
--
Atenciosamente,
Prof. Carlos A. S. de Andrade
LAPEA - Laboratório de Pesquisa em Economia Aplicada e Engenharia de
Produção
Universidade Federal de Campina Grande.
Centro de Humanidades
Unidade Acadêmica de Economia
10 years, 5 months

Re: [Gretl-users] GARCH, Forecasting
by Allin Cottrell

On Mon, 17 Jan 2011, [ISO-8859-1] Alejandro Mosi�o wrote:
> Maybe i was not too much specific last time:
>
> I have a variable "y" that follows a GARCH(1,1) process. Then, i Gretl i
> type:
>
> garch 1 1 ; y const
>
> Then i got the result and forecasting the out-of-sample values of y can
> be done in the usual way. However, i'm interested in forecasting the
> out-of-sample variance. I don't know if such a function exists in Gretl.
There is no built-in function to do this, but you can compute a
one-step ahead forecast of the variance from the model data, as
hown in the following example script.
<script>
open b-g.gdt
garch 1 1 ; Y
series e = $uhat
series h = $h
dataset addobs 10
a0 = $coeff[2]
a1 = $coeff[3]
b1 = $coeff[4]
series hfc = h
# set future errors to their expectation
e = misszero(e)
# forecast the variance
hfc = a0 + a1 * e(-1)^2 + b1 * hfc(-1)
smpl 1970 ;
print e h hfc --byobs
</script>
Allin Cottrell
10 years, 10 months

Deterministic trend in VAR
by Muheed Jamaldeen

Hi all,
Just a general VAR related question. When is it appropriate to include
a deterministic time trend in the reduced form VAR? Visually some of the
data series (not all) look like they have trending properties. In any case,
does the inclusion of the time trend matter if the process is stable and
therefore stationary (i.e. the polynomial defined by the determinant of the
autoregressive operator has no roots in and on the complex unit circle)
without the time trend term. Other than unit root tests, is there a better
way to test whether the underlying data generating process has a stochastic
or deterministic process?
I am mainly interested in the impulse responses.
Cheers,
Mj
11 years, 7 months

Retrieving the roots of an ARIMA
by Henrique Andrade

Dear Gretl Community,
Is there any way to retrieve the roots of an ARIMA model? Is there an
accessor that allows this kind of operation?
My aim goal is to build an automatic ARIMA modelling script that saves only
the models with signicant parameters and roots outside the unit circle.
Many thanks,
Henrique Andrade
11 years, 7 months

GRETL CRASH
by Hebert Suárez Cahuana

I have a problem for a long time, it begin with 1.9.5 version I can't open
any file, neither to do any operation, Gretl crash and close,
my system is ubuntu 10.4 and I did install Gretl using tar.files.
I try next:
- Delete file gretl2rc
- Compiling using *./configure --disable-sse2*
but my problem continue, I send us message from my console
hebert@hebert-desktop:~$ gretl
Couldn't read /home/hebert/.gretl2rc
get_gretl_charset: using UTF-8
Descomprimiendo 146981 bytes de los datos...
Instrucción ilegal
hebert@hebert-desktop:~$
Thank you for your time, but what can I do to solve this problem?
Sincerely
Hebert Suarez Cahuana
Departamento de Economía
Universidad Nacional de San Agustín
Arequipa-Perú
11 years, 8 months

Download for Mac
by Dominic Balestrieri

Although there is an extremely helpful and informative page online regarding the installation of Gretl on a Mac, Gretl does not want to work on my system as well as the Apple products of a few of my classmates. We all have downloaded the appropriate software (X11, GTK, etc.) and I have tried both the latest release of the product as well as the current snapshot but neither seem to work. Once the software is downloaded and dragged into the applications section (which normally installs most software automatically), I attempt to open Gretl and instead of opening, the program immediately terminates. Any suggestions?
Thanks,
Dominic Balestrieri
11 years, 8 months

manual calculating
by clarodina＠lycos.com

ols d1 const d2 and the std error of d2 is 0.351919
d1
1 -0.9371
2 -0.40054
3 1.963222
4 -0.3328
5 -0.82194
6 1.085598
7 -0.9985
8 0.763004
9 -0.94785
10 0.047204
d2
1 -0.26785
2 -0.67142
3 -1.07196
4 0.891262
5 0.558466
6 -0.26347
7 0.822125
8 -0.17638
9 0.586626
10 -0.3612
Use s = sqrt[ ∑ ((e_i)^2/(n-2)) / (∑ (x_i - xbar)^2) ] for manually calculating the std error and the value is 0.88583 and does not match the one on gretl
What are the proper steps to do the manual calculating ?
11 years, 8 months

Issue with the line break character in the gretl editor
by Beek Pang

Dear gretl community,
I am using gretl 1.7.4 under MS-Windows XP (Service Pack 2). My issue and question is the following:
When using the gretl editor to write a piece of code, I have to split a command over several lines. Specifically, with a panel dataset, I need to restrict the sample by just keeping a small number of the firms included in the full dataset. I tried to do this in various ways, but only one way appears to be feasible, as follows:
% code snippet begin ----
smpl --restrict firm=2 || \
firm=5 || \
firm=11
% code snippet end ----
My problem is that my subsample will contain many more than just 3 firms (over 30 firms, that is), and when I code this in the way demonstrated above and run the code, gretl unfortunately does not restrict the sample exactly as I say in the code. Specifically, (a) firms appear in the subsample which are unwanted (like in the above example, having firm 17 in it), and also, (b) some firms I want to have are missing (like in the above example, not having firm 5 in it).
I understand that the gretl character for splitting commands over several lines is the "\" character. However, in my case at least, it seems that when the number of lines over which the splitting takes place is larger, the command may not work properly.
Could anyone of you provide an idea what may be going on or an idea how to solve resp. work around this problem, please? I'd appreciate this very much.
Many many thanks in advance.
Beek
11 years, 8 months

manual calculating
by clarodina＠lycos.com

Using 4 data point
price
11 385
12 505
13 425
14 415
sqft
11 2254
12 2600
13 2800
14 3000
The std error of sqft on gretl is 0.112376
Using the formula
s = sqrt[ ∑ ((e_i)^2/(n-2)) / (∑ (x_i - xbar)^2) ]
x_i = the ith observation
e_i = the ith error = y_i - yhat_i
n = sample size
xbar = mean of the x values
gives 0.012628336
11 years, 8 months

manual calculating
by clarodina＠lycos.com

ols d1 const d2 and have the std error of d2
what is the formula for calculating std error of d2? a manual calculating of std error does not match the one on gretl
11 years, 8 months