Bookmark and Share

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


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

st: Logit maximum likelihood in mata code


From   nick bungy <[email protected]>
To   "[email protected]" <[email protected]>
Subject   st: Logit maximum likelihood in mata code
Date   Fri, 19 Apr 2013 08:34:12 +0100

Dear Statalist,
I'm having trouble setting up the optimizer to find the maximum likelihood of a logit model. I'm still learning the syntax and set up of mata, though I've tried to follow 'help mf_optimize' as best I can.
Could someone assist in where I am going wrong with the code?
----------
sysuse auto, clear
mata
st_view(x=0,.,("weight"))
st_view(y=0,.,("foreign"))
x=x,J(rows(x),1,1)
void logistic(todo, p, y, x, llf, g, H)
{
b = p[1,1::2]
One =J(rows(x),1,1)
llf = y'*log(One:/One+exp(-(x*b)))+(One-y)'*log(One:/One+exp(-(x*b)))
}
 S = optimize_init()
 optimize_init_evaluator(S, &logistic())
 optimize_init_params(S, 0)
 optimize_init_argument(S, 1, y)
 optimize_init_argument(S, 2, x)
 optimize_init_which(S,"max")
 p = optimize(S)
-----------
Many thanks,
Nicholas 		 	   		  
*
*   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/


© Copyright 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index