Specify log-likelihood function interactively
Optionally specify first derivatives
Robust SEs to relax distributional assumptions
Cluster–robust SEs for correlated data
Linear and nonlinear postestimation hypotheses tests
Maximization of user-specified likelihood functions has long been a hallmark of Stata, but you have had to write a program to calculate the log-likelihood function. Now it is even easier. The only requirements are that you be able to write the log likelihood for individual observations and that the log likelihood for the entire sample be the sum of the individual values.
Stata can fit probit models, but let’s write our own.
The log-likelihood function for probit is
\(LL(y) = ln(normal(x'b))\;\;\;\;\;\;if\;\;y==1\)
\(\;\;\;\;\;\;\;\;\;\;= ln(normal(-xb))\;\;\;\;if\;\;y==0\)
To fit a model of outcome foreign on mpg and price, we type
. sysuse auto
(1978 automobile data)
. mlexp (cond(foreign==1, ln(normal({xb:mpg price} + {b0})),
ln(normal(-1*({xb:} + {b0})))))
Initial: Log likelihood = -51.292891
Alternative: Log likelihood = -51.724316
Rescale: Log likelihood = -46.186316
Rescale eq: Log likelihood = -44.952041
Iteration 0: Log likelihood = -44.952041
Iteration 1: Log likelihood = -36.332989
Iteration 2: Log likelihood = -36.266131
Iteration 3: Log likelihood = -36.266068
Iteration 4: Log likelihood = -36.266068
Maximum likelihood estimation
Log likelihood = -36.266068 Number of obs = 74
| Coefficient Std. err. z P>|z| [95% conf. interval] | ||
| xb | ||
| mpg | .1404876 .0373599 3.76 0.000 .0672635 .2137117 | |
| price | .0001571 .0000641 2.45 0.014 .0000315 .0002827 | |
| /b0 | -4.592058 1.115921 -4.12 0.000 -6.779223 -2.404893 | |
Those results are exactly the same as those produced by Stata’s probit.
Read more in Maximum Likelihood Estimation with Stata, Fifth Edition by Jeffrey Pitblado, Brian Poi, and William Gould.
See the manual entry. Read In the spotlight: mlexp
mlexp is an easy-to-use interface into Stata’s more advanced maximum-likelihood programming tool that can handle far more complex problems; see the documentation for ml.
ml itself is an easier-to-use interface into Stata’s most advanced optimization programs found in Stata’s matrix language; see the documentation for moptimize(), optimize(), solvenl(), and deriv(). see the documentation for Stata’s gmm.
