Stefano Fachin | 17 Dec 09:54 2014
Picon

Monte Carlo simulation

dear Alessandra,
although this list is not meant to do students' assignments, your sincere admission deserves a friendly hand :-)

On the spot I can see two problems
  • you must always fix the seed of the random number generator to make sure you are always using the same numbers (for instance, set seed 1234). If this is not clear have a look at the way random numbers are generated, even Wikipedia will do.
  • to appreciate the effect of increasing sample size you must compare estimates computed from N observations and from a larger sample including those observations plus some more. This is more easily done the other way round: create a dataset, compute your stuff, throw away some observations, compute same stuff, compare.

good luck!
Stefano

-- _________________________________________________________________________ Stefano Fachin Professore Ordinario di Statistica Economica Dip. di Scienze Statistiche Università di Roma "La Sapienza" P.le A. Moro 5 - 00185 Roma - Italia Tel. +39-06-49910834 fax +39-06-49910072 web http://stefanofachin.site.uniroma1.it/
<div>
    dear Alessandra,<br>
      although this list is not meant to do students' assignments, your
      sincere admission deserves a friendly hand :-)<br><br>
      On the spot I can see two problems<br>
    <ul>
<li>you must always fix the seed of the random number
          generator to make sure you are always using the same numbers
        (for instance, set seed 1234). If this is not clear have
          a look at the way random numbers are generated, even Wikipedia
          will do.<br>
</li>
      <li>to appreciate the effect of increasing
          sample size you must compare estimates computed from N
          observations and from a larger sample including those
          observations plus some more. This is more easily done the
          other way round: create a dataset, compute your stuff, throw
          away some observations, compute same stuff, compare.</li>
    </ul>
<p>good luck!<br>
      Stefano<br></p>
    -- 
_________________________________________________________________________

Stefano Fachin
Professore Ordinario di Statistica Economica
Dip. di Scienze Statistiche
Universit&agrave; di Roma "La Sapienza"
P.le A. Moro 5 - 00185 Roma - Italia
Tel. +39-06-49910834
fax  +39-06-49910072
web <a class="moz-txt-link-freetext" href="http://stefanofachin.site.uniroma1.it/">http://stefanofachin.site.uniroma1.it/</a>

  </div>
Alessandra .Cruanes Aguilar | 16 Dec 14:30 2014
Picon

Monte Carlo Simulation

Dear all,
I have been having some troubles computing a Monte Carlo simulation.
I am a student, so please don't be too horrified by my short experience :)

The problem is the following:
I am requested to perform a MC simulation on a lagged-dependent variable model with autocorrelated residuals. The estimator for the lagged-dependent variable, the only regressor, should be inconsistent and biased.
My concern is that decreasing the sample size the bias decreases, and I guess that that's just wrong.
(I also tried using robust std errors, and nothing changes!)

here's the code I used:

nulldata 200
setobs --time-series

scalar n=$nobs

scalar beta1=0.8
scalar rho=0.4

smpl 1 1
series u=0
series y=0

smpl 2 200
series e=randgen(N,0,1)
series u=rho*u(-1)+e
series y=beta1*y(-1)+u


ols y y(-1)  --simple


loop 5000 --progressive --quiet


series e=randgen(N,0,1)
series u=rho*u(-1)+e
series y=beta1*y(-1)+u

ols y y(-1)

scalar beta1hat= $coeff(y_1)
scalar s1= $stderr(y_1)
scalar bias=$coeff(y_1)-beta1
genr LB = beta1hat - critical(t,$df,0.025)*s1
genr UB = beta1hat + critical(t,$df,0.025)*s1
print  beta1 beta1hat bias LB UB

endloop


smpl 50 --random --replace

loop 5000 --progressive --quiet
   
series e=randgen(N,0,1)
series u=rho*u(-1)+e
series y=beta1*y(-1)+u

ols y y(-1)

scalar beta1hat= $coeff(y_1)
scalar s1= $stderr(y_1)
scalar bias=$coeff(y_1)-beta1
genr LB = beta1hat - critical(t,$df,0.025)*s1
genr UB = beta1hat + critical(t,$df,0.025)*s1
print  beta1 beta1hat bias LB UB

endloop

Thank you so much
<div><div dir="ltr">
<div>
<div>
<div>
<div>
<div>
<div>
<div>Dear all, <br>
</div>I have been having some troubles computing a Monte Carlo simulation. <br>
</div>I am a student, so please don't be too horrified by my short experience :)<br><br>
</div>The problem is the following: <br>
</div>I am requested to perform a MC simulation on a lagged-dependent variable model with autocorrelated residuals. The estimator for the lagged-dependent variable, the only regressor, should be inconsistent and biased.<br>
</div>My concern is that decreasing the sample size the bias decreases, and I guess that that's just wrong.<br>
</div>
<div>(I also tried using robust std errors, and nothing changes!)<br>
</div>
<div><br></div>here's the code I used: <br><br>
</div>
<blockquote class="gmail_quote">
<span>nulldata 200</span><br><span>setobs --time-series </span><br><span></span><br><span>scalar n=$nobs</span><br><span></span><br><span>scalar beta1=0.8</span><br><span>scalar rho=0.4</span><br><span></span><br><span>smpl 1 1 </span><br><span>series u=0</span><br><span>series y=0</span><br><span></span><br><span>smpl 2 200</span><br><span>series e=randgen(N,0,1)</span><br><span>series u=rho*u(-1)+e</span><br><span>series y=beta1*y(-1)+u</span><br><span></span><br><span></span><br><span>ols y y(-1)&nbsp; --simple </span><br><br><span></span><br><span>loop 5000 --progressive --quiet</span><br><span></span><br><span></span><br><span>series e=randgen(N,0,1)</span><br><span>series u=rho*u(-1)+e</span><br><span>series y=beta1*y(-1)+u</span><br><span></span><br><span>ols y y(-1) </span><br><span></span><br><span>scalar beta1hat= $coeff(y_1)</span><br><span>scalar s1= $stderr(y_1)</span><br><span>scalar bias=$coeff(y_1)-beta1</span><br><span>genr LB = beta1hat - critical(t,$df,0.025)*s1</span><br><span>genr UB = beta1hat + critical(t,$df,0.025)*s1</span><br><span>print&nbsp; beta1 beta1hat bias LB UB </span><br><span></span><br><span>endloop</span><br><span></span><br><span></span><br><span>smpl 50 --random --replace</span><br><span></span><br><span>loop 5000 --progressive --quiet</span><br><span>&nbsp;&nbsp;&nbsp; </span><br><span>series e=randgen(N,0,1)</span><br><span>series u=rho*u(-1)+e</span><br><span>series y=beta1*y(-1)+u</span><br><span></span><br><span>ols y y(-1) </span><br><span></span><br><span>scalar beta1hat= $coeff(y_1)</span><br><span>scalar s1= $stderr(y_1)</span><br><span>scalar bias=$coeff(y_1)-beta1</span><br><span>genr LB = beta1hat - critical(t,$df,0.025)*s1</span><br><span>genr UB = beta1hat + critical(t,$df,0.025)*s1</span><br><span>print&nbsp; beta1 beta1hat bias LB UB </span><br><span></span><br><span>endloop</span><br>
</blockquote>
<div>
<span></span><br>
</div>
<div>Thank you so much<br>
</div>
</div></div>
JOSE FRANCISCO PERLES RIBES | 10 Dec 08:37 2014
Picon

fortnightly data

Dear list:

I know that this is a very basic question. But how can I introduce fortnightly data in Gretl?. I have a series hotel occupancy delivered each two weeks and I want to analyze it.

I have used gretl GUI with the non-standard frequencies, but my result is always non-sense. If I use 24 frequencies (12 months x 2 pairs of weeks) Gretl interpret them as 'hourly' data.

Thanks in advance and sorry for any inconvenience.

José Perles
University of Alicante


<div><div dir="ltr">
<div>
<div>
<div>
<div>Dear list:<br>
</div>
<br>I know that this is a very basic question. But how can I introduce fortnightly data in Gretl?. I have a series hotel occupancy delivered each two weeks and I want to analyze it. <br><br>I have used gretl GUI with the non-standard frequencies, but my result is always non-sense. If I use 24 frequencies (12 months x 2 pairs of weeks) Gretl interpret them as 'hourly' data. <br><br>
</div>Thanks in advance and sorry for any inconvenience.<br><br>
</div>Jos&eacute; Perles<br>
</div>University of Alicante<br><div><div><div>
<br><br>
</div></div></div>
</div></div>
Allin Cottrell | 10 Dec 02:54 2014
Picon

progress indicator for time-consuming scripts

This is in response to Peter Summers' observation in
http://lists.wfu.edu/pipermail/gretl-users/2014-December/010481.html

It's a long story but I'll try to be brief.

Prior to gretl 1.9.91 we had a mechanism that appeared in the 
menubar of a script editor window to indicate progress when a script 
took appreciable time to complete: a "spinner" plus a "stop" button 
that could be used to halt execution of the script. (At that time 
the output window didn't appear until execution of the script was 
finished.)

More recently, I figured it was preferable to open a script output 
window right away, and show the spinner + stop-button in that 
window. In this way, we could arrange for partial output to appear 
as it was produced, giving a more convincing impression that 
progress was being made (see the newish "flush" command).

That worked up to a point, but after Peter's comment I realized that 
the policy "open an output window right away and show a spinner and 
stop-button there" was not always engaged; it depended, in a way 
that I hadn't intended, on certain user choices.

I think this is now fixed in CVS and snapshots. Testing would be 
welcome. If you run a time-consuming script in the GUI you should 
see the output window "come to the front" with spinner and stopper. 
(But if the script completes quickly you probably won't notice 
this.)

This is quite tricky to code, and I'd be particularly interested if 
anyone is able to provoke a crash (e.g. by pressing the stop 
button).

Allin Cottrell
Logan Kelly | 8 Dec 23:46 2014

Question about join

I am using the join command and getting the following error

 

'2013q4' does not match the format '%Yq%q'

 

But I cannot figure out why the date does not match the format string. I am probably just making a silly mistake.

 

 

Thanks,

 

Logan

--

Logan J. Kelly, Ph.D.

Associate Professor, Department of Economics, University of Wisconsin-River Falls

 

<div>
<div class="WordSection1">
<p class="MsoNormal">I am using the join command and getting the following error<p></p></p>
<p class="MsoNormal"><p>&nbsp;</p></p>
<p class="MsoNormal">'2013q4' does not match the format '%Yq%q'<p></p></p>
<p class="MsoNormal"><p>&nbsp;</p></p>
<p class="MsoNormal">But I cannot figure out why the date does not match the format string. I am probably just making a silly mistake.<p></p></p>
<p class="MsoNormal"><p>&nbsp;</p></p>
<p class="MsoNormal"><p>&nbsp;</p></p>
<p class="MsoNormal">Thanks,<p></p></p>
<p class="MsoNormal"><p>&nbsp;</p></p>
<p class="MsoNormal">Logan<p></p></p>
<p class="MsoNormal">-- <p></p></p>
<p class="MsoNormal">Logan J. Kelly, Ph.D.<p></p></p>
<p class="MsoNormal">Associate Professor, Department of Economics, University of Wisconsin-River Falls<p></p></p>
<p class="MsoNormal"><p>&nbsp;</p></p>
</div>
</div>
Miles Higbie | 6 Dec 23:17 2014
Picon

Cross Country GDP Growth

Hello I was trying to find the Real GDP Growth rates by comparing to countries and my teacher gave me this script to do so 

= (1/10) ∗ ln(Y r1970/Y r1960)

but it is not working I was wondering what is the issue, it keeps saying syntax but I do not know what to do. 

Thanks   

<div><div dir="ltr">Hello I was trying to find the Real GDP Growth rates by comparing to countries and my teacher gave me this script to do so&nbsp;<br><br><div class="" title="Page 45"><div class=""><div class=""><p><span>g&nbsp;</span><span>= (1</span><span>/</span><span>10)&nbsp;</span><span>&lowast;&nbsp;</span><span>ln</span><span>(</span><span>Y r</span><span>1970</span><span>/Y r</span><span>1960)<br><br>but it is not working I was wondering what is the issue, it keeps saying syntax but I do not know what to do.&nbsp;<br><br>Thanks &nbsp;&nbsp;</span></p></div></div></div>
</div></div>
Pindar | 6 Dec 18:34 2014
Picon

Problem with new binary data file format and a question concerning join command

Hi there,

I'm using gretl to construct panels and load data in via the great join command - thanks for developing this feature!
When I tried to save the final data file in the new gdtb format something went wrong.
gretl saves a file but crashes when opening it.
Below is the the hansl script to produce the error.
In terms of the join command: a compound condition of four and more elements is not supported, or?

Have a nice St. Nicholas' Day
Leon

#****************
set echo off
set messages off
nulldata 10 --preserve

scalar Y1 = 2001
scalar Y2=Y1 + 25

#Level 1
matrix M1 = \
{510\
;520}

string file = "markers_Panel_"
sprintf stamp "%d", abs(round(randgen1(z, 0, 1)*randgen1(z, 0, 1)*randgen1(i, 50, 200)))
file += stamp
file += ".txt"
print file

outfile " <at> file" --write
loop i=1..rows(M1) --quiet
      loop j = Y1..Y2 --quiet
           printf "%g/%g\n", M1[i], j
      endloop
  endloop
outfile --close

scalar N = rows(M1)
scalar T = (Y2-Y1+1)
scalar counts = N*T
nulldata counts --preserve
setobs T  1:01 --stacked-time-series
series BVNR = M1**ones(T,1)
setinfo BVNR --description="Unit ID"
series time = ones(N,1)**seq(Y1,Y2)'
setinfo time --description="Years"
delete index
list lGroups = BVNR time
discrete lGroups
setobs BVNR time --panel-vars
sprintf strY1 "%g", Y1
setobs 1 <at> strY1 --panel-time
series time_gretl = $obsdate
markers --from-file=" <at> file"

store "testPanel.gdt"
open "testPanel.gdt"
#store "testPanel.gdtb"
#open "testPanel.gdtb"
#************************
<div>
    Hi there,<br><br>
    I'm using gretl to construct panels and load data in via the great
    join command - thanks for developing this feature!<br>
    When I tried to save the final data file in the new gdtb format
    something went wrong.<br>
    gretl saves a file but crashes when opening it.<br>
    Below is the the hansl script to produce the error.<br>
    In terms of the join command: a compound condition of four and more
    elements is not supported, or?<br><br>
    Have a nice St. Nicholas' Day<br>
    Leon<br><br>
    #****************<br>
    set echo off<br>
    set messages off<br>
    nulldata 10 --preserve<br><br>
    scalar Y1 = 2001<br>
    scalar Y2=Y1 + 25<br><br>
    #Level 1<br>
    matrix M1 = \<br>
    {510\<br>
    ;520}<br><br>
    string file = "markers_Panel_"<br>
    sprintf stamp "%d", abs(round(randgen1(z, 0, 1)*randgen1(z, 0,
    1)*randgen1(i, 50, 200)))<br>
    file += stamp<br>
    file += ".txt"<br>
    print file<br><br>
    outfile " <at> file" --write<br>
    loop i=1..rows(M1) --quiet<br>
    &nbsp;&nbsp;&nbsp;&nbsp;&nbsp; loop j = Y1..Y2 --quiet<br>
    &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; printf "%g/%g\n", M1[i], j<br>
    &nbsp;&nbsp;&nbsp;&nbsp;&nbsp; endloop<br>
    &nbsp; endloop<br>
    outfile --close<br><br>
    scalar N = rows(M1)<br>
    scalar T = (Y2-Y1+1)<br>
    scalar counts = N*T<br>
    nulldata counts --preserve<br>
    setobs T&nbsp; 1:01 --stacked-time-series<br>
    series BVNR = M1**ones(T,1)<br>
    setinfo BVNR --description="Unit ID"<br>
    series time = ones(N,1)**seq(Y1,Y2)'<br>
    setinfo time --description="Years"<br>
    delete index<br>
    list lGroups = BVNR time<br>
    discrete lGroups<br>
    setobs BVNR time --panel-vars<br>
    sprintf strY1 "%g", Y1<br>
    setobs 1  <at> strY1 --panel-time<br>
    series time_gretl = $obsdate<br>
    markers --from-file=" <at> file"<br><br>
    store "testPanel.gdt"<br>
    open "testPanel.gdt"<br>
    #store "testPanel.gdtb"<br>
    #open "testPanel.gdtb"<br>
    #************************<br>
</div>
Summers, Peter | 4 Dec 23:14 2014

broken "in-progress" wheel?

Folks,

 

Something seems to have happened to the “in-progress” wheel that should appear at the top of an executing script. At least on my Win7 machine with 1.10.0 cvs, build date 12/2, the attached script runs, but there’s no wheel (or stop button).

 

TIA,

 

PS

 

 

Attachment (no_wheel.inp): application/octet-stream, 207 bytes
<div>
<div class="WordSection1">
<p class="MsoNormal">Folks,<p></p></p>
<p class="MsoNormal"><p>&nbsp;</p></p>
<p class="MsoNormal">Something seems to have happened to the &ldquo;in-progress&rdquo; wheel that should appear at the top of an executing script. At least on my Win7 machine with 1.10.0 cvs, build date 12/2, the attached script runs, but there&rsquo;s no wheel (or stop button).
<p></p></p>
<p class="MsoNormal"><p>&nbsp;</p></p>
<p class="MsoNormal">TIA,<p></p></p>
<p class="MsoNormal"><p>&nbsp;</p></p>
<p class="MsoNormal">PS<p></p></p>
<p class="MsoNormal"><p>&nbsp;</p></p>
<p class="MsoNormal"><p></p></p>
<p class="MsoNormal"><p>&nbsp;</p></p>
</div>
</div>
Stefano Fachin | 1 Dec 11:26 2014
Picon

functions on Gretl server: trivial suggestion

Given that the issue of the functions available on the server is currently debated I add a (very) trivial suggestion that may add some usability at zero cost. Since the number of functions available is growing, and will hopefully grow even more rapidly, it would be useful to set the standard of describing them with a phrase starting with one or two relevant keywords. For instance,  the functions "bootstrap Chow test VAR models" and "Structural VARs" would become "VAR bootstrap Chow test" and "VAR structural" and would be next to each other in the alphabetic list and immediately found by a user looking for VAR routines.
bye,
Stefano
-- _________________________________________________________________________ Stefano Fachin Professore Ordinario di Statistica Economica Dip. di Scienze Statistiche Università di Roma "La Sapienza" P.le A. Moro 5 - 00185 Roma - Italia Tel. +39-06-49910834 fax +39-06-49910072 web http://stefanofachin.site.uniroma1.it/
<div>
    Given that the issue of the functions available on the server is
    currently debated I add a (very) trivial
      suggestion that may add some usability at zero cost. Since the
      number of functions available is growing, and will hopefully grow
      even more rapidly, it would be useful to set the standard of
      describing them with a phrase starting with one or two relevant
      keywords. For instance,&nbsp; the functions "bootstrap Chow
      test VAR models" and "Structural VARs"
    would become "VAR bootstrap Chow test" and
      "VAR structural" and would be next to each other in the alphabetic
      list and immediately found by a user looking for VAR routines.<br>
      bye,<br>
      Stefano<br>
    -- 
_________________________________________________________________________

Stefano Fachin
Professore Ordinario di Statistica Economica
Dip. di Scienze Statistiche
Universit&agrave; di Roma "La Sapienza"
P.le A. Moro 5 - 00185 Roma - Italia
Tel. +39-06-49910834
fax  +39-06-49910072
web <a class="moz-txt-link-freetext" href="http://stefanofachin.site.uniroma1.it/">http://stefanofachin.site.uniroma1.it/</a>

  </div>
guido | 27 Nov 16:50 2014
Picon

join command - syntiax

Hi all
I am sorry tho ask help. Before asking here i studied the newest copy of the Guide, sought in the list whitout result.

I am surely making a trivial mistake using "join" command but i am unable to bypass it by myself. 

I want to join variable CHIUSURA in a2.gdt, with a1.gdt

a1.gdt
obs	ch1
2014-01-02	0,8000
2014-01-03	0,8425
2014-01-06	0,8485
2014-01-07	0,9060
2014-01-08	0,8790
2014-01-09	0,8660
2014-01-10	0,8370
2014-01-13	0,8690
2014-01-14	0,8625
2014-01-15	0,8560

a2.gdt
obs	CHIUSURA
2014-01-02	19,97
2014-01-03	21,40
2014-01-06	22,08
2014-01-07	21,55
2014-01-08	21,81
2014-01-09	21,49
2014-01-10	20,86
2014-01-13	21,00
2014-01-14	21,10
2014-01-15	21,00

this is the script

#open the left hand database
open /home/guido/gretl/Star/a1.gdt
#join the CHIUSURA var in a2.gdt
join /home/guido/gretl/Star/a2.gdt CHIUSURA

this is the output log 

gretl versione 1.9.91
Sessione corrente: 2014-11-27 16:35

#open the left hand database
? open /home/guido/gretl/Star/a1.gdt

Lettura del file dati /home/guido/gretl/Star/a1.gdt
Periodicità: 5, oss. max.: 10
Intervallo delle osservazioni: 2014-01-02-2014-01-15

2 variabili elencate:
  0) const    1) ch1    

#join the CHIUSURA var in a2.gdt
? join /home/guido/gretl/Star/a2.gdt CHIUSURA
[Sorry, the command is not available for this estimator]

Errore nell'esecuzione dello script: abbandono
> join /home/guido/gretl/Star/a2.gdt CHIUSURA

Thx for any suggestion.

Guido

Attachment (Join-problem.inp): text/gretl.script, 192 bytes
Attachment (a2.gdt): application/gretl.data, 1084 bytes
Attachment (a1.gdt): application/gretl.data, 1088 bytes
Hi all
I am sorry tho ask help. Before asking here i studied the newest copy of the Guide, sought in the list whitout result.

I am surely making a trivial mistake using "join" command but i am unable to bypass it by myself. 

I want to join variable CHIUSURA in a2.gdt, with a1.gdt

a1.gdt
obs	ch1
2014-01-02	0,8000
2014-01-03	0,8425
2014-01-06	0,8485
2014-01-07	0,9060
2014-01-08	0,8790
2014-01-09	0,8660
2014-01-10	0,8370
2014-01-13	0,8690
2014-01-14	0,8625
2014-01-15	0,8560

a2.gdt
obs	CHIUSURA
2014-01-02	19,97
2014-01-03	21,40
2014-01-06	22,08
2014-01-07	21,55
2014-01-08	21,81
2014-01-09	21,49
2014-01-10	20,86
2014-01-13	21,00
2014-01-14	21,10
2014-01-15	21,00

this is the script

#open the left hand database
open /home/guido/gretl/Star/a1.gdt
#join the CHIUSURA var in a2.gdt
join /home/guido/gretl/Star/a2.gdt CHIUSURA

this is the output log 

gretl versione 1.9.91
Sessione corrente: 2014-11-27 16:35

#open the left hand database
? open /home/guido/gretl/Star/a1.gdt

Lettura del file dati /home/guido/gretl/Star/a1.gdt
Periodicità: 5, oss. max.: 10
Intervallo delle osservazioni: 2014-01-02-2014-01-15

2 variabili elencate:
  0) const    1) ch1    

#join the CHIUSURA var in a2.gdt
? join /home/guido/gretl/Star/a2.gdt CHIUSURA
[Sorry, the command is not available for this estimator]

Errore nell'esecuzione dello script: abbandono
> join /home/guido/gretl/Star/a2.gdt CHIUSURA

Thx for any suggestion.

Guido

Jan Tille | 25 Nov 13:51 2014
Picon

Random Effects Probit output

Dear Grelt list members,

 

I run a random effects probit regression and was wondering, why the output displays p-values, though the –p-values option was not selected. When I estimate the model as a pooled (panel) probit, then Gretl displays the slopes, which corresponds to the command description.

 

Is there another option (accessor variable, etc.) which enables one to retrieve the average marginal effects – averaged over each entity and instead of evaluating the effects at the average of the independent variables? I ask because I am using some binary independent variables, and evaluating the marginal effects at some value in between would not make much sense for these variables.

 

FYI the LR test that tests Ho: rho=0 is rejected with a p-value   0.000173

 

Thanks in advance.

 

Jan

 

 

<div><div class="WordSection1">
<p class="MsoNormal"><span>Dear Grelt list members,<p></p></span></p>
<p class="MsoNormal"><span><p>&nbsp;</p></span></p>
<p class="MsoNormal"><span lang="EN-US">I run a random effects probit regression and was wondering, why the output displays p-values, though the &ndash;p-values option was not selected. When I estimate the model as a pooled (panel) probit, then Gretl displays the slopes, which corresponds to the command description.<p></p></span></p>
<p class="MsoNormal"><span lang="EN-US"><p>&nbsp;</p></span></p>
<p class="MsoNormal"><span lang="EN-US">Is there another option (accessor variable, etc.) which enables one to retrieve the average marginal effects &ndash; averaged over each entity and instead of evaluating the effects at the average of the independent variables? I ask because I am using some binary independent variables, and evaluating the marginal effects at some value in between would not make much sense for these variables.<p></p></span></p>
<p class="MsoNormal"><span lang="EN-US"><p>&nbsp;</p></span></p>
<p class="MsoNormal"><span lang="EN-US">FYI the LR test that tests Ho: rho=0 is rejected with a p-value &nbsp;&nbsp;0.000173<p></p></span></p>
<p class="MsoNormal"><span lang="EN-US"><p>&nbsp;</p></span></p>
<p class="MsoNormal"><span lang="EN-US">Thanks in advance.<p></p></span></p>
<p class="MsoNormal"><span lang="EN-US"><p>&nbsp;</p></span></p>
<p class="MsoNormal"><span lang="EN-US">Jan<p></p></span></p>
<p class="MsoNormal"><span lang="EN-US"><p>&nbsp;</p></span></p>
<p class="MsoNormal"><span lang="EN-US"> </span><span lang="EN-US"><p></p></span></p>
<p class="MsoNormal"><span lang="EN-US"><p>&nbsp;</p></span></p>
</div></div>

Gmane