Re: [Gretl-users] SUR models what methods is used?
by Allin Cottrell
On Wed, 30 Mar 2011, Jean-Baptiste Combes wrote:
> I have been using Gretl recently to estimate proportion of staff, I have
> three groups and the sum of the three proportion equals to 1. According to
> Wooldridge (2002) this can of "share" systems can be estimated by SUR models
> with Feasible GLS estimation (p. 167). Accordingly I can remove one
> equation.
>
> This is one of the models I estimate
> "Skill-Mix Gap" <- system
> equation pNHDfteHT2 const cvnbbeds avgnbbeds nbhospital Found TypeHT_1
> TypeHT_2 TypeHT_4 TypeHT_5 gapNCo0305recod gapHCo0305recod gapMCo0305recod
> equation pHDNfteHT2 const cvnbbeds avgnbbeds nbhospital Found TypeHT_1
> TypeHT_2 TypeHT_4 TypeHT_5 gapNCo0305recod gapHCo0305recod gapMCo0305recod
> endog pNHDfteHT2 pHDNfteHT2
> instr const cvnbbeds avgnbbeds nbhospital Found TypeHT_1 TypeHT_2 TypeHT_4
> TypeHT_5 gapNCo0305recod gapHCo0305recod gapMCo0305recod
> end system
>
> estimate "Skill-Mix Gap" method=sur --iterate
>
> The estimation is computed, no problems
>
> I put iterate but the estimation is done with just one iteration. In the
> command GRETL reference book I read that with iterate the estimation is the
> maximum likelihood one.
>
> I am completely lost because I would like to know how does that work, I
> would prefer to have FGLS as in Wooldridge (my reference book in
> econometrics).
Non-iterated SUR is FGLS; the --iterate flag calls for iteration
of FGLS to the ML solution. However it appears you have identical
regressors in your two equations, in which case FGLS is equivalent
to equation-by-equation OLS -- so it's not surprising that only
one iteration is taken. See for example the System chapter
in William Greene's Econometric Analysis.
I notice that your system contains "endog" and "instr"
specifications. These will be ignored in estimation via SUR, which
is not a full-blown "simultaneous equations" estimator: the
"system" aspect of SUR is just recognition of the cross-equation
correlation of the error terms.
Allin Cottrell
13 years
Re: [Gretl-users] Resampling time series data
by Allin Cottrell
On Tue, 29 Mar 2011, artur bala wrote:
> Le 29/03/2011 18:46, Anutechia Asongu a �crit :
> > To put my point plain, my main dataset is "daily", but I'll like to
> > work with weekly observations.
> >
> Try to compact the daily data onto weekly data (Menu: Data -> Compact data)
Or use the "dataset" command.
But I just noticed that compaction from daily to weekly had a bug
in the case where the daily data had "hidden" missing values (i.e.
certain days are just dropped from the dataset as if they didn't
exist, rather being included with NA values for the variables).
The bug led to some usable data being dropped at the end of the
series. This is now fixed in CVS and the gretl snapshots for
Windows and OS X.
Allin Cottrell
13 years
Re: [Gretl-users] FEVD plot in gretl and GNU R
by Allin Cottrell
On Mon, 28 Mar 2011, Grzegorz Konat wrote:
> First of all, thank you [Jack] so much for the script - works
> perfectly fine for me!
In fact, the FEVD is available internally in gretl. I've now added
an accessor, $fevd, so you can grab it as a matrix.
> As far as the issue with different estimates is concerned [...]
>
> In gretl I do:
>
> vecm 2 1 X Y Z --ct
>
> However, when I use R's (urca):
>
> xyz.vecm <- ca.jo(gretldata[, c("X", "Y", "Z")], type = "trace", ecdet =
> "trend", K = 2, spec = "transitory") /for all options in 'type' and
> 'spec'/
>
> and transform obtained VECM into VAR representation:
>
> vec2var.xyz <- vec2var(xyz.vecm, r = 1)
>
> the system I get has quite different parameters [...]
The model you're estimating in R is equivalent to using the --crt
flag (constant plus restricted trend) in gretl. If you use --crt
you should find that the VAR coefficients agree pretty well.
Allin Cottrell
13 years
FEVD plot in gretl and GNU R
by Grzegorz Konat
Dear All,
I wonder, if there's any way to plot final error variance decomposition
(FEVD) output, produced after VAR or VECM, in gretl?
So far, the only way I know is to export data to GNU R and plot FEVD there.
This approach, however, has its disadvantages, as one has to estimate the
whole system in R first and R's estimates often differ significantly from
those obtained with gretl.
Many thanks in advance!
Greg
13 years
Ralph M Rodriguez/PO/KAIPERM is out of the office.
by Ralph.M.Rodriguez＠kp.org
I will be out of the office starting 03/28/2011 and will not return until
04/04/2011.
Hi All, I will be out of the office on business from Mar 28 through Apr
1,returning to the office Apri 4.
Please, if you have an immediate concern regarding Cost Model or
Construction Economics, please email or contact Bradley A Njus, 510 625
4595, or email me and/or call me at 51o 421 3863 with your questions.
Best Regards,
Ralph
13 years
Re: [Gretl-users] Gretl-users Digest, Vol 50, Issue 31
by Data Analytics Corp.
Hi,
I appreciate the feedback. But this seems like a lot of work just to
add a few lines. Nonetheless, I'll try it.
Thanks,
Walt
________________________
Walter R. Paczkowski, Ph.D.
Data Analytics Corp.
44 Hamilton Lane
Plainsboro, NJ 08536
________________________
(V) 609-936-8999
(F) 609-936-3733
walt(a)dataanalyticscorp.com
www.dataanalyticscorp.com
_____________________________________________________
On 3/24/2011 12:00 PM, gretl-users-request(a)lists.wfu.edu wrote:
> 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. Drawing lines on a scatter plot (Allin Cottrell)
> 2. Re: Drawing lines on a scatter plot (Allin Cottrell)
>
>
> ----------------------------------------------------------------------
>
> Message: 1
> Date: Wed, 23 Mar 2011 15:06:05 -0400 (EDT)
> From: Allin Cottrell<cottrell(a)wfu.edu>
> Subject: [Gretl-users] Drawing lines on a scatter plot
> To: Gretl users<gretl-users(a)lists.wfu.edu>
> Message-ID:<Pine.A41.4.58.1103231504480.393216(a)f1n11.sp2net.wfu.edu>
> Content-Type: TEXT/PLAIN; charset=US-ASCII
>
> I'm forwarding this (which got bounced by mistake).
>
> Allin Cottrell
>
> Date: Wed, 23 Mar 2011 13:32:43 -0400
> From: Data Analytics Corp.<walt(a)dataanalyticscorp.com>
> To: gretl-users(a)lists.wfu.edu
> Subject: Drawing lines on a scatter plot
>
> Hi,
>
> I created a simple scatter plot of the log of sales (l_Sales) on the
> vertical axis and the log of price (l_Price) on the horizontal. Now I
> want to draw a vertical line and a horizontal line, both at their
> respective means. I tried to edit the graph and add a line using the
> Lines tab. I enter a formula such as mean(l_Price). But I got an
> error: How can I add the lines? Any suggestions are appreciated.
>
> Thanks,
>
> Walt
>
> ________________________
>
> Walter R. Paczkowski, Ph.D.
> Data Analytics Corp.
> 44 Hamilton Lane
> Plainsboro, NJ 08536
> ________________________
> (V) 609-936-8999
> (F) 609-936-3733
> walt(a)dataanalyticscorp.com
> www.dataanalyticscorp.com
> _____________________________________________________
>
>
>
> ------------------------------
>
> Message: 2
> Date: Wed, 23 Mar 2011 15:27:51 -0400 (EDT)
> From: Allin Cottrell<cottrell(a)wfu.edu>
> Subject: Re: [Gretl-users] Drawing lines on a scatter plot
> To: Gretl list<gretl-users(a)lists.wfu.edu>
> Message-ID:<Pine.A41.4.58.1103231517040.393216(a)f1n11.sp2net.wfu.edu>
> Content-Type: TEXT/PLAIN; charset=US-ASCII
>
> On Wed, 23 Mar 2011, Walt wrote:
>
>> I created a simple scatter plot of the log of sales (l_Sales) on the
>> vertical axis and the log of price (l_Price) on the horizontal. Now I
>> want to draw a vertical line and a horizontal line, both at their
>> respective means. I tried to edit the graph and add a line using the
>> Lines tab. I enter a formula such as mean(l_Price). But I got an
>> error: How can I add the lines? Any suggestions are appreciated.
> Formulas entered via the GUI graph editor are fed directly to
> gnuplot, which doesn't know about "l_Price". However,
>
> (a) You can add the y-mean by looking up that variable's summary
> statistics in gretl and using the graph editor to add a line at
> that value. For example, if the y-mean is 3.65, just enter a
> "formula" of "3.65".
>
> (b) Adding the x-mean (a vertical line) is more awkward and you'll
> probably have to edit the gnuplot commands. (Save the graph "as an
> icon" then right-click the icon.) One way is to append a plot
> "line" using a single data-point, with x-value equal to the x-mean
> and y-value equal to the natural height of the graph. Here's an
> example, based on a scatter plot of price against sqft from
> gretl's data4-1:
>
> Before addition of vertical line:
>
> plot \
> '-' using 1:($2) notitle w points, \
> 52.35090729 + 0.1387503195*x title "Y = 52.4 + 0.139X" w lines, \
> 317.49 title "mean(price)" w lines lt 3
> 1065 199.9
> 1254 228
> [...]
> e
>
> After addition:
>
> plot \
> '-' using 1:($2) notitle w points, \
> 52.35090729 + 0.1387503195*x title "Y = 52.4 + 0.139X" w lines, \
> 317.49 title "mean(price)" w lines lt 3, \
> '-' using 1:2 title "mean(sqft)" w impulses lt 3
> 1065 199.9
> 1254 228
> [...]
> e
> 1910.9 550
> e
>
> In gnuplot "e" on a line by itself signals the end of an inline
> data block.
>
> Allin Cottrell
>
>
>
>
> ------------------------------
>
> _______________________________________________
> Gretl-users mailing list
> Gretl-users(a)lists.wfu.edu
> http://lists.wfu.edu/mailman/listinfo/gretl-users
>
> End of Gretl-users Digest, Vol 50, Issue 31
> *******************************************
>
13 years, 1 month
Re: [Gretl-users] Drawing lines on a scatter plot
by Allin Cottrell
On Wed, 23 Mar 2011, Walt wrote:
> I created a simple scatter plot of the log of sales (l_Sales) on the
> vertical axis and the log of price (l_Price) on the horizontal. Now I
> want to draw a vertical line and a horizontal line, both at their
> respective means. I tried to edit the graph and add a line using the
> Lines tab. I enter a formula such as mean(l_Price). But I got an
> error: How can I add the lines? Any suggestions are appreciated.
Formulas entered via the GUI graph editor are fed directly to
gnuplot, which doesn't know about "l_Price". However,
(a) You can add the y-mean by looking up that variable's summary
statistics in gretl and using the graph editor to add a line at
that value. For example, if the y-mean is 3.65, just enter a
"formula" of "3.65".
(b) Adding the x-mean (a vertical line) is more awkward and you'll
probably have to edit the gnuplot commands. (Save the graph "as an
icon" then right-click the icon.) One way is to append a plot
"line" using a single data-point, with x-value equal to the x-mean
and y-value equal to the natural height of the graph. Here's an
example, based on a scatter plot of price against sqft from
gretl's data4-1:
Before addition of vertical line:
plot \
'-' using 1:($2) notitle w points, \
52.35090729 + 0.1387503195*x title "Y = 52.4 + 0.139X" w lines, \
317.49 title "mean(price)" w lines lt 3
1065 199.9
1254 228
[...]
e
After addition:
plot \
'-' using 1:($2) notitle w points, \
52.35090729 + 0.1387503195*x title "Y = 52.4 + 0.139X" w lines, \
317.49 title "mean(price)" w lines lt 3, \
'-' using 1:2 title "mean(sqft)" w impulses lt 3
1065 199.9
1254 228
[...]
e
1910.9 550
e
In gnuplot "e" on a line by itself signals the end of an inline
data block.
Allin Cottrell
13 years, 1 month
Drawing lines on a scatter plot
by Allin Cottrell
I'm forwarding this (which got bounced by mistake).
Allin Cottrell
Date: Wed, 23 Mar 2011 13:32:43 -0400
From: Data Analytics Corp. <walt(a)dataanalyticscorp.com>
To: gretl-users(a)lists.wfu.edu
Subject: Drawing lines on a scatter plot
Hi,
I created a simple scatter plot of the log of sales (l_Sales) on the
vertical axis and the log of price (l_Price) on the horizontal. Now I
want to draw a vertical line and a horizontal line, both at their
respective means. I tried to edit the graph and add a line using the
Lines tab. I enter a formula such as mean(l_Price). But I got an
error: How can I add the lines? Any suggestions are appreciated.
Thanks,
Walt
________________________
Walter R. Paczkowski, Ph.D.
Data Analytics Corp.
44 Hamilton Lane
Plainsboro, NJ 08536
________________________
(V) 609-936-8999
(F) 609-936-3733
walt(a)dataanalyticscorp.com
www.dataanalyticscorp.com
_____________________________________________________
13 years, 1 month
Re: [Gretl-users] Lag Order for ADF Test
by Allin Cottrell
On Mon, 21 Mar 2011, Giuseppe Vittucci wrote:
> Btw, I was wondering why in the gretl output for panel unit root tests
> the information criteria, which might be useful to select the right lag
> order, are not reported by default.
I've now added printing of AIC, BIC and HQC when the --verbose
option is given with the "adf" or "kpss" command.
Allin Cottrell
13 years, 1 month
