I am aware of two main approaches:
1. -constraint- is for setting up linear constraints on parameters. This
is the easiest way to apply constraints, providing that it applies to
your case, possibly after a parameterisation trick or two.
2. You write your own programs to maximise likelihood, or more generally
optimise some figure of merit, so that your constraint is automatically
satisfied. That's a lot of fun.
Others may have better news. I did -findit scale returns- and found
nothing obvious. You may need to use better keywords.
Note that if you restrict yourself to economics terminology, you tend to
get only economics replies.
Nick
[email protected]
Rup Singh
i am running with panel data some growth equations, in which i need to
restrict some
parameters to imply constant returns to scale. can anyone help in the
commands to be
used for re, fe, be, abond or dpd models.
*
* 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/
