Statalist


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

st: putting constraint on self-written program using ml d0


From   "J. Li" <lij53@univmail.cis.mcmaster.ca>
To   statalist@hsphsun2.harvard.edu
Subject   st: putting constraint on self-written program using ml d0
Date   Wed, 26 Aug 2009 16:54:06 -0400

Hi all,

I wrote a program using ml package with d0 method. The purpose of the
program is similar with the ordered probit regression command oprobit.
 After I define the program, I would like to impose some constraints on
the parameter of the cut-off values. E.g. I use ml model as

ml model d0 etai (hlthc=age gender index, nocons) /a1 /a2 /a3 /a4,
constraint (1)

where a1 a2 a3 a4 are four seperate equations defined in the program to
substitute in four cut-off values with "mleval" (we have 5 outcomes of
y in the data). How can I define the constraint? When I tried 

constraint 1 define [eq2]_cons=1.45

or 

constraint 1 define [eq2]a1=1.45

it gave me some error message. Do you know the reason for this? Thanks
a lot!

Jinhu 
*
*   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