Re: st: constraining the cut points in ordered probit

[Richard Williams <Richard.A.Williams.5@ND.edu>]

At 08:15 PM 1/22/2007, Gutierrez, Italo wrote:
> Hi all,
>
> I want to constraint the cut points (four in total) in an ordered Probit
> model. Apparently, the oprobit command does not allow you to do that. I
> am trying to use the linest command, but I don't know how to set up the
> restrictions. Has anybody done it before? I will appreciate any
> suggestions you can give me that would spare me from having to program
> the ML estimation.
>
> Thanks in advance,
>
> Italo
-oglm- (available from SSC) lets you impose constraints.  Example:

. use "http://www.indiana.edu/~jslsoc/stata/spex_data/ordwarm2.dta";
(77 & 89 General Social Survey)

. constraint 1 [cut1]_cons = -1

. constraint 2 [cut2]_cons = -.3

. constraint 3 [cut3]_cons = 1

. oglm  warm yr89 male white age ed prst, link(probit) c(1 2 3)

Ordered Probit Regression                         Number of obs   =       2293
                                                  Wald chi2(6)    =     275.01
                                                  Prob > chi2     =     0.0000
Log likelihood = -2925.1085                       Pseudo R2       =     0.0236

 ( 1)  [cut1]_cons = -1
 ( 2)  [cut2]_cons = -.3
 ( 3)  [cut3]_cons = 1
------------------------------------------------------------------------------
        warm |      Coef.   Std. Err.      z    P>|z|     [95% Conf. Interval]
-------------+----------------------------------------------------------------
        yr89 |   .2942007   .0465962     6.31   0.000     .2028739    .3855275
        male |  -.4002846    .044647    -8.97   0.000    -.4877911    -.312778
       white |  -.1806917   .0654782    -2.76   0.006    -.3090267   -.0523568
         age |  -.0101478   .0011115    -9.13   0.000    -.0123262   -.0079693
          ed |     .04509   .0071941     6.27   0.000     .0309898    .0591903
        prst |   .0031986   .0019201     1.67   0.096    -.0005648    .0069621
-------------+----------------------------------------------------------------
       /cut1 |         -1          .        .       .            .           .
       /cut2 |        -.3          .        .       .            .           .
       /cut3 |          1          .        .       .            .           .
------------------------------------------------------------------------------

The support page for oglm is at

http://www.nd.edu/~rwilliam/oglm/index.html

Alternatively, you could use linest after oprobit, setting up the 
constraints like the above.


-------------------------------------------
Richard Williams, Notre Dame Dept of Sociology
OFFICE: (574)631-6668, (574)631-6463
FAX:    (574)288-4373
HOME:   (574)289-5227
EMAIL:  Richard.A.Williams.5@ND.Edu
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/