|
|  |
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
RE: st: Ordered Probit with Panel Data [reoprob]
What are the proportion of cases in each category of denentry? You have many categories and if one of them is very small than that might cause problems. In that case I would combine the small category with a neighbour. If that doesn't work than I don't know.
-----------------------------------------
Maarten L. Buis
Department of Social Research Methodology
Vrije Universiteit Amsterdam
Boelelaan 1081
1081 HV Amsterdam
The Netherlands
visiting adress:
Buitenveldertselaan 3 (Metropolitan), room Z214
+31 20 5986715
http://home.fsw.vu.nl/m.buis/
-----------------------------------------
-----Original Message-----
From: [email protected] [mailto:[email protected]]On Behalf Of ALICE DOBSON
Sent: dinsdag 11 april 2006 19:04
To: [email protected]
Subject: RE: st: Ordered Probit with Panel Data [reoprob]
Thanks Maarten. It makes no difference.
>From: "Maarten Buis" <[email protected]>
>Reply-To: [email protected]
>To: <[email protected]>
>Subject: RE: st: Ordered Probit with Panel Data [reoprob]
>Date: Tue, 11 Apr 2006 18:56:51 +0200
>
>type:
>version 8.2
>oprobit denentry totalpsl inctotpsl ldvolperpsl incldvolperpsl pslperixc
>incpslperixc c1
>
>
>see -whelp version-
>
>-----------------------------------------
>Maarten L. Buis
>Department of Social Research Methodology
>Vrije Universiteit Amsterdam
>Boelelaan 1081
>1081 HV Amsterdam
>The Netherlands
>
>visiting adress:
>Buitenveldertselaan 3 (Metropolitan), room Z214
>
>+31 20 5986715
>
>http://home.fsw.vu.nl/m.buis/
>-----------------------------------------
>
>-----Original Message-----
>From: [email protected]
>[mailto:[email protected]]On Behalf Of ALICE DOBSON
>Sent: dinsdag 11 april 2006 18:57
>To: [email protected]
>Subject: RE: st: Ordered Probit with Panel Data [reoprob]
>
>Thanks Maarten. I tried the former but to no difference. For the second, I
>use Stata 9.1, how can I use version 8.2?
>.
>
>
> >From: "Maarten Buis" <[email protected]>
> >Reply-To: [email protected]
> >To: <[email protected]>
> >Subject: RE: st: Ordered Probit with Panel Data [reoprob]
> >Date: Tue, 11 Apr 2006 18:49:04 +0200
> >
> >One thing you want to do is rescale your explanatory variables, (e.g.
> >divide totalpsl by 1,000,000) so you get more meaningful parameters. This
> >sometimes also helps with errors like the ones you have. If it doesn't
>help
> >use Richard's suggestion to start with -version 8.2-.
> >
> >-----------------------------------------
> >Maarten L. Buis
> >Department of Social Research Methodology
> >Vrije Universiteit Amsterdam
> >Boelelaan 1081
> >1081 HV Amsterdam
> >The Netherlands
> >
> >visiting adress:
> >Buitenveldertselaan 3 (Metropolitan), room Z214
> >
> >+31 20 5986715
> >
> >http://home.fsw.vu.nl/m.buis/
> >-----------------------------------------
> >
> >-----Original Message-----
> >From: [email protected]
> >[mailto:[email protected]]On Behalf Of ALICE DOBSON
> >Sent: dinsdag 11 april 2006 18:43
> >To: [email protected]
> >Subject: Re: st: Ordered Probit with Panel Data [reoprob]
> >
> >Thanks a lot Richards.
> >
> >Here is the oprob command line.
> >
> >reoprob denentry totalpsl inctotpsl ldvolperpsl incldvolperpsl pslperixc
> >incpslperixc c1, i(sac)
> >where sac is the panel ID variable
> >
> >
> >
> >Please find below the oprobit estimates with the same variables.
> >
> >
> >oprobit denentry totalpsl inctotpsl ldvolperpsl incldvolperpsl pslperixc
> >incpslperixc c1
> >
> >Iteration 0: log likelihood = -819.32506
> >Iteration 1: log likelihood = -804.45505
> >Iteration 2: log likelihood = -802.44132
> >Iteration 3: log likelihood = -801.99999
> >Iteration 4: log likelihood = -801.98951
> >Iteration 5: log likelihood = -801.9895
> >
> >Ordered probit regression Number of obs =
> >2185
> > LR chi2(7) =
> >34.67
> > Prob > chi2 =
> >0.0000
> >Log likelihood = -801.9895 Pseudo R2 =
> >0.0212
> >
> >------------------------------------------------------------------------------
> > denentry | Coef. Std. Err. z P>|z| [95% Conf.
> >Interval]
> >-------------+----------------------------------------------------------------
> > totalpsl | -8.61e-07 2.48e-07 -3.47 0.001 -1.35e-06
> >-3.75e-07
> > inctotpsl | .0000117 4.92e-06 2.39 0.017 2.10e-06
> >.0000214
> >ldvolperpsl | -.0663414 .0484572 -1.37 0.171 -.1613158
> >.028633
> >incldvolpe~l | -.0190692 .1165205 -0.16 0.870 -.2474451
> >.2093067
> > pslperixc | .0000134 3.16e-06 4.23 0.000 7.19e-06
> >.0000196
> >incpslperixc | 3.54e-06 4.28e-06 0.83 0.408 -4.85e-06
> >.0000119
> > c1 | -.0090175 .0030619 -2.95 0.003 -.0150187
> >-.0030163
> >-------------+----------------------------------------------------------------
> > /cut1 | .5188891 .3154155 -.0993139
> >1.137092
> > /cut2 | 1.050361 .3172624 .4285386
> >1.672184
> > /cut3 | 1.257379 .3195799 .6310139
> >1.883744
> > /cut4 | 1.400535 .321929 .7695659
> >2.031504
> > /cut5 | 1.568453 .325447 .9305884
> >2.206317
> > /cut6 | 1.735414 .3309201 1.086822
> >2.384005
> > /cut7 | 1.811064 .3343915 1.155669
> >2.46646
> > /cut8 | 2.132501 .3601558 1.426609
> >2.838393
> > /cut9 | 2.261056 .3785036 1.519202
> >3.002909
> >
> >
> > >From: Richard Williams <[email protected]>
> > >Reply-To: [email protected]
> > >To: [email protected]
> > >Subject: Re: st: Ordered Probit with Panel Data [reoprob]
> > >Date: Tue, 11 Apr 2006 11:00:18 -0500
> > >
> > >At 09:50 AM 4/11/2006, ALICE DOBSON wrote:
> > >>HI all,
> > >>I use Stata 9.1. I apologise for repeating this question in case
>someone
> > >>already addressed the same and I missed it. I had earlier posted this
> > >>question on Mar 29, 06.
> > >>
> > >>I ran an oprobit with a panel data and got the estimates. Of course,
>the
> > >>regression model does not consider the panel nature of the data. But,
> >when
> > >>I am running an reoprob with exactly the same variables I get the
> > >>following message.
> > >>
> > >>conformability error
> > >>r(503);
> > >
> > >Alice, perhaps you could show us the exact command you gave? My wild
> >guess
> > >is that either (a) you've got a syntax error, or (b) there is some sort
> >of
> > >multicollinearity problem. But, it is hard to say without more
>details.
> > >
> > >
> > >-------------------------------------------
> > >Richard Williams, Notre Dame Dept of Sociology
> > >OFFICE: (574)631-6668, (574)631-6463
> > >FAX: (574)288-4373
> > >HOME: (574)289-5227
> > >EMAIL: [email protected]
> > >WWW (personal): http://www.nd.edu/~rwilliam
> > >WWW (department): http://www.nd.edu/~soc
> > >
> > >*
> > >* For searches and help try:
> > >* http://www.stata.com/support/faqs/res/findit.html
> > >* http://www.stata.com/support/statalist/faq
> > >* http://www.ats.ucla.edu/stat/stata/
> >
> >_________________________________________________________________
> >FREE pop-up blocking with the new MSN Toolbar - get it now!
> >http://toolbar.msn.click-url.com/go/onm00200415ave/direct/01/
> >
> >*
> >* For searches and help try:
> >* http://www.stata.com/support/faqs/res/findit.html
> >* http://www.stata.com/support/statalist/faq
> >* http://www.ats.ucla.edu/stat/stata/
> >
> >*
> >* For searches and help try:
> >* http://www.stata.com/support/faqs/res/findit.html
> >* http://www.stata.com/support/statalist/faq
> >* http://www.ats.ucla.edu/stat/stata/
>
>_________________________________________________________________
>Express yourself instantly with MSN Messenger! Download today - it's FREE!
>http://messenger.msn.click-url.com/go/onm00200471ave/direct/01/
>
>*
>* For searches and help try:
>* http://www.stata.com/support/faqs/res/findit.html
>* http://www.stata.com/support/statalist/faq
>* http://www.ats.ucla.edu/stat/stata/
>
>*
>* For searches and help try:
>* http://www.stata.com/support/faqs/res/findit.html
>* http://www.stata.com/support/statalist/faq
>* http://www.ats.ucla.edu/stat/stata/
_________________________________________________________________
Express yourself instantly with MSN Messenger! Download today - it's FREE!
http://messenger.msn.click-url.com/go/onm00200471ave/direct/01/
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
