Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: st: RE: Heckman two-step estimator


From   Sridhar Telidevara <sridhar.telidevara@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: RE: Heckman two-step estimator
Date   Sun, 14 Feb 2010 10:07:13 -0500

I ran the same program that you sent me. It fits the individual models
but not the full model.

. clear*

.
. cmp setup

.
. webuse laborsup

.
. gen byte kids2 = kids + int(uniform()*3)

.
. cmp (kids=fem_educ) (kids2=fem_educ), ind($cmp_oprobit $cmp_oprobit) nolr

Fitting individual models as starting point for full model fit.

Iteration 0:   log likelihood = -800.76494
Iteration 1:   log likelihood = -800.48687
Iteration 2:   log likelihood = -800.48687

:::::results:::::::

Fitting full model.

               cmp_lnL():  3499  ghk2setup() not found
                 <istmt>:     -  function returned error
r(3499);

.
. tech(dfp) qui
unrecognized command:  tech
r(199);


Error 3499: The specified variable or function could not be found.
        In the case of a function, it was not already loaded, it is not
        in the libraries, and there is no .mo file with its name.


Sridhar


On Sun, Feb 14, 2010 at 9:41 AM, Martin Weiss <martin.weiss1@gmx.de> wrote:
>
> <>
>
> This example runs without a hitch for me:
>
> *************
> clear*
> cmp setup
> webuse laborsup
> gen byte kids2 = kids + int(uniform()*3)
> cmp (kids=fem_educ) (kids2=fem_educ), ind($cmp_oprobit $cmp_oprobit) nolr
> tech(dfp) qui
> *************
>
>
> You may want to -ssc uninstall cmp- and then -ssc inst cmp-.
>
> What does -which cmp- give you?
>
>
> HTH
> Martin
>
> -----Ursprüngliche Nachricht-----
> Von: owner-statalist@hsphsun2.harvard.edu
> [mailto:owner-statalist@hsphsun2.harvard.edu] Im Auftrag von Sridhar
> Telidevara
> Gesendet: Sonntag, 14. Februar 2010 15:34
> An: statalist@hsphsun2.harvard.edu
> Betreff: Re: st: RE: Heckman two-step estimator
>
> Thank you Martin. I ran a bivariate seeming unrelated ordered probit
> just to understand the command. It says ghk2setup() not found.
> However, ghk2 is already installed and the software is up-to-date. I
> am using stata11. I also ran an example given in the help. It says the
> same. Searched web to learn more about ghk2setup() but no clue as to
> what is happening.
>
> Any thoughts?
>
> Thanks,
>
> Sridhar
>
> On Sun, Feb 14, 2010 at 4:47 AM, Martin Weiss <martin.weiss1@gmx.de> wrote:
>>
>> <>
>>
>> Have you tried -ssc d cmp-?
>>
>>
>> HTH
>> Martin
>>
>> -----Original Message-----
>> From: owner-statalist@hsphsun2.harvard.edu
>> [mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of Sridhar
>> Telidevara
>> Sent: Sonntag, 14. Februar 2010 08:08
>> To: statalist@hsphsun2.harvard.edu
>> Subject: st: Heckman two-step estimator
>>
>> How would one go about estimating Heckman two-step estimator if both
>> the stages involve ordinal outcomes. Say the first stage has 5 levels
>> and the second stage has 3 levels. How would one calculate
>> inverse-mills ratio in the first step and incorporate them in the
>> second step. I would highly appreciate your help.
>>
>> Thanks,
>>
>> Sridhar
>> *
>> *   For searches and help try:
>> *   http://www.stata.com/help.cgi?search
>> *   http://www.stata.com/support/statalist/faq
>> *   http://www.ats.ucla.edu/stat/stata/
>>
>> *
>> *   For searches and help try:
>> *   http://www.stata.com/help.cgi?search
>> *   http://www.stata.com/support/statalist/faq
>> *   http://www.ats.ucla.edu/stat/stata/
>>
>
> *
> *   For searches and help try:
> *   http://www.stata.com/help.cgi?search
> *   http://www.stata.com/support/statalist/faq
> *   http://www.ats.ucla.edu/stat/stata/
>
>
> *
> *   For searches and help try:
> *   http://www.stata.com/help.cgi?search
> *   http://www.stata.com/support/statalist/faq
> *   http://www.ats.ucla.edu/stat/stata/
>

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index