Statalist The Stata Listserver

[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: ML programming

From   Daniel Lawson <>
Subject   st: ML programming
Date   Fri, 23 Mar 2007 16:11:26 -0400

Dear StataListers,

I have read [p] and maximum likelihood estimation with stata third
edition, but am a bit confused something.

In the ml model statement, one calls a program to evaluate the
likelihood.  Is there a way to pass arguments to this program that do
not correspond with theta parameters to be estimated by ml?

For instance, if I wanted to code a tobit command with a variable
censoring threshold, where the threshold for each observation was
contained in a variable, and the observation was censored if it
equaled that variable, but was not censored if it was less than that
variable, how can I pass the name of the threshold variable to the
function that calculated the likelihood?

I can hard-code the name of the threshold variable into the
likelihood function, or I could create a global macro with the name
of the threshold variable, but neither of these seem like elegant
solutions.  Is there a way to pass arguments to the likelihood
function in ml without making ml think that the argument is another
parameter to be computed?

Daniel Lawson

Daniel Lawson
Assistant Professor of Economics
Drew University

*   For searches and help try:

© Copyright 1996–2017 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index