gretl questions- quantile regression
by Deborah
Hi Allin and Jack,
I have a few questions for you. I'm trying to analyze a data set
using quantile regression. Your software is incredibly easy to use
and offers a lot of great options for this kind of analysis. But I'd
like to do a non-linear quantile regression? Is this possible? As a
second question, is there a way, using gretl, to test for
heteroskedasticity in order to decide which options are best for the
regression?
Thanks for the help (and the great program!),
Deborah
16 years, 3 months
System SUR and OLS....
by Mariusz Doszyń
Hello....
It is known that while estimating system of equations by using SUR and OLS estimator we obtain the same results when matrix of independent variables (X) is identical in each equation. I've tried this and results are ... different. Maybe you could figure out why?
I've attached files (with data and script). Could this be effect of cross equation residuals correlations or it's just ... an error?
With regard...
Mariusz
Poland
16 years, 3 months
SPSS data in gretl
by Allin Cottrell
Hello all,
There's a fair amount of large-scale survey data available on the
net in SPSS format. Over the last couple of years several of my
students have wanted to make use of such data. Up to now I've
helped them out by importing from SPSS to R, then exporting as CSV
for gretl.
This works OK but it's not very convenient and it loses some
useful information (mainly, descriptive labels for variables and
'value labels' for categorical variables). So I've recently added
to gretl an importer for SPSS .sav files. I've tested on a
variety of such files, but if anyone is in the habit of handling
SPSS data and could give the importer a work-out, that would be
great.
Allin Cottrell
16 years, 3 months
Re: [Gretl-users] ECM and VECM
by Yuniarto Hadiwibowo
Thank you for your attention. I am still learning this ECM and VECM.
Some people point out to me several issues in VECM:
1. Small sample bias.
2. Data should be integrated in order(1).
<script>
open data10-5
loop foreach j nc c ct ctt gls --quiet
loop foreach i calwage uswage --quiet
adf 4 $i --$j --test-down --quiet
lt_$i$j=$test
lp_$i$j=$pvalue
adf 4 $i --$j --difference --test-down --quiet
dt_$i$j=$test
dp_$i$j=$pvalue
end loop
end loop
loop foreach j nc c ct ctt gls --quiet
printf "\nADF $j\n \t\t%10s \t%12s \n", "Level", "Difference"
printf "\t\t%5s [%6s] %5s [%6s]\n", "tvalue", "pvalue", "tvalue", "pvalue"
loop foreach i calwage uswage --quiet
printf "$i \t%6.3f [%6.4f] %6.3f [%6.4f]\n", lt_$i$j, lp_$i$j, dt_$i$j, dp_$i$j
end loop
end loop
</script>
I cannot find how to access the lag order in ADF test. Is there any accessor for the actual lag order used?
Considering small sample data and ADF test result, can we use VECM?
Yuniarto Hadiwibowo
----- Original Message ----
From: Allin Cottrell <cottrell(a)wfu.edu>
To: Gretl list <gretl-users(a)lists.wfu.edu>
Sent: Tuesday, December 9, 2008 2:21:40 AM
Subject: Re: [Gretl-users] ECM
<script>
open data10-5
coint2 2 calwage uswage
vecm 2 1 calwage uswage
restrict
a[2] = 0
end restrict --verbose
</script>
The "restrict" block tests the hypothesis that the US wage does
not error-correct in response to perturbations to the California
wage, which is implicitly assumed in the single-equation
specification; this hypothsis is rejected at the 5 percent level.
Allin Cottrell
16 years, 3 months
aggregate or disaggregate
by Hodgess, Erin
Dear Gretl Users:
Are there any functions to either aggregate or disaggregate data,
please?
If so, would there be any interest in them, please?
Thanks,
Erin
Erin M. Hodgess, Ph.D.
Associate Professor
Department of Computer and Mathematical Sciences
University of Houston - Downtown
mailto: hodgesse(a)uhd.edu
16 years, 3 months
To Allin...
by Mariusz Doszyń
Hello Allin...
I have a question to you which doesn't fit to list's profile. I've sent you an e-mail (cottrell(a)wfu.edu) but response didn't appear. Does it mean 'no' or maybe I should send you an e-mail on different address?
Thanks in advance...
With regard,
Mariusz Doszyń
Poland
PS. Sorry for using list for 'this' but I couldn't figure out different option.
16 years, 3 months
ECM
by Yuniarto Hadiwibowo
Hello,
I'd like to know how to solve this ECM equation in Gretl:
dy = b[1] + b[2] dx + b[3] ( y(-1) - b[5] x(-1) )
With b[4]=b[3]*b[5],
dy = b[1] + b[2] dx + b[3] y(-1) - b[4] x(-1)
Using OLS we can have coefficient, t-value, and p-value of:
b[1], b[2], b[3], and b[4]
<script>
open data10-5
ols diff(calwage) const diff(uswage) lags(1,calwage) lags(1,uswage)
</script>
How to get coefficient, t-value, and p-value of b[5] itself?
Thank you.
Yuniarto Hadiwibowo
16 years, 3 months
System of equations
by Mariusz Doszyń
Hello....
I wonder if you could give some simple applications of using sur method or, generally, system of equations. Maybe I've missed something but couldn't find any examples in accessible documentation...
With regard,
Mariusz
Poland
16 years, 3 months
ADF result
by Charles Ward
I ran a ADF test in gretl and in R.
(The regression was no constant, LNEG lagged once, d_LNEG lag1 and d_LNEG
lag2)
In gretl and R, the results were for most purposes identical for all numbers
for Z and d_LNEG lag 1
In gretl the results for d_LNEG lag2 were
coefficient std. error t-ratio p-value
d_LNEG_2 -0.470623 0.126295 -3.726 0.2006
But in R the results were
z.diff.lag2 -0.47062 0.12629 -3.726 0.00053
Which is correct?
Charles W
16 years, 3 months
Periods in forecast variance decomposition
by Tim Cox
Hi, everyone.
After estimating a VAR, Gretl offers a forecast variance decomposition under
the "analysis" menu. The dialogue box requires the user to select at least
two periods for the forecast variance decomposition, which makes me wonder
why two periods are required ... if I select two periods, is the first one
the last "in sample" period and the second one the first (and only) forecast
period? Or, if not, what do the two periods represent?
Thanks,
Tim Cox
16 years, 3 months
