Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.

# st: ml non-linear model

 From "Miguel Angel Duran" To Subject st: ml non-linear model Date Thu, 25 Apr 2013 18:50:23 +0200

```I have estimated a non-linear function by means of ml. This is my first time
using ml. I would just like to be sure that I am doing things in a right
way. So if anyone could please check the following or make any
recommendation, I'd be very grateful.

My equation is,

vdmean = a*mvlagmean + b*vlagmean^c*(1-vlagmean)

Accordingly, I have done this in Stata,

. program datos3mean
1. version 10.1
2. args lnf theta1 theta2 theta3 sigma
3. quietly replace `lnf' = ln(normalden(\$ML_y1, `theta1' + `theta2' *
vlagmean^`theta3' * (1-vlagmean), `sigma'))
4. end

. ml model lf datos3mean (vdmean=mvlagmean, nocons) (theta2:) (theta3:)
(sigma:), vce(robust)

. ml check

RESULT: datos3mean HAS PASSED ALL TESTS

. ml maximize

...
Iteration 27:  log pseudolikelihood =  223.93681

Number of obs   =
66
Wald chi2(1)    =
14.61
Log pseudolikelihood =  223.93681                 Prob > chi2     =
0.0001

----------------------------------------------------------------------------
--
|               Robust
vdmean |      Coef.   Std. Err.      z    P>|z|     [95% Conf.
Interval]
-------------+--------------------------------------------------------------
--
eq1          |
mvlagmean |   .0171285   .0044818     3.82   0.000     .0083442
.0259127
-------------+--------------------------------------------------------------
--
theta2       |
_cons |   .2233535    .110224     2.03   0.043     .0073184
.4393886
-------------+--------------------------------------------------------------
--
theta3       |
_cons |   12.01406   5.432059     2.21   0.027     1.367416
22.6607
-------------+--------------------------------------------------------------
--
sigma        |
_cons |   .0081322   .0013922     5.84   0.000     .0054036
.0108608
----------------------------------------------------------------------------
--

Miguel.

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/
```