st: ML Max Non-Linear

[Steven Archambault <archstevej@gmail.com>]

Hi all,

I have a clarification question on some non-linear programming, which
includes defining my log-likelihood function as follows:

-quietly gen double `sigma'=exp(`eta')-
-quietly replace
`lnL'=-.5*ln(2*_pi)-.5*ln((`sigma')^2)-.5*(yindx-`xb')^2/(`sigma')^2-

I am ensuring sigma is positive.

The results show eta as not significant (see below). I assume this is
not a big deal, just says that the null that eta is not equal to 0.
Here is the question In this case, do I just assume sigma is 1?

Coef.                            Std. Err.                        z
 P>|z|     [95% Conf. Interval]

eta          |  _cons |   1.165659   1.636503     0.71   0.476
-2.041827    4.373146

Thanks for your help on this one.

-Steve
*
*   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/