Dear Statalisters,
I wrote the following simple ado file (as a pure exercise of
-ml-) to run an OLS model via -ml-:
...
The two results are virtually the same, but slightly different
as well; I'm afraid estimation results by -ml- are less
significant (ex.z-value vs.t-value, chi2 vs.F or R-squared),
though they may not be directly comparable.
So my question is, (suppose the above ado file is correct)
how one should interpret these two results (esp.the one by
-ml-).
Incorrect assumption, alas! I suggest looking at Stata's Maximum
Likelihood book: