Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: RE: Initial values maximum likelihood

From   "FEIVESON, ALAN H. (AL) (JSC-SK) (NASA)" <[email protected]>
To   "'[email protected]'" <[email protected]>
Subject   st: RE: Initial values maximum likelihood
Date   Fri, 16 Apr 2004 10:33:36 -0500

Alejandro - There is a rather arcane description of how to set initial
values on pp.115-6 of the ml-manual. Perhaps I can save you some frustration
by giving you a simple example where you are only setting values for the
"constant" terms in each linear combination:

ml model lf radpow (zal:`1'= ) (zbe:`3') (ga: ) 
ml init  zal:_cons=-5.0  /zbe:_cons=-3.5 /ga:_cons=1.5  

Quite often, however, the reason you get the "could not find feasible
values" message is because something is wrong with the way your likelihood
is calculated (trying to take log of a negative number, or partially missing
data, etc)

Hope this helps

Al Feiveson

-----Original Message-----
From: [email protected]
[mailto:[email protected]]On Behalf Of
[email protected]
Sent: Thursday, April 15, 2004 3:01 PM
To: [email protected]
Subject: st: Initial values maximum likelihood

Hi all,

How do you set initial values in a maximum likelihood

I am trying to run a ML program using lf and d0 but with ML
search the computer can't find values to solve my program
using ml search and I get the message "could not find
feasible values" does that mean that my program is wrong?
When I run ml check it stops after test 2 and gives back the
same error message. Can I solve this by specifying inital


Alejandro Lopez-Feldman
Ph.D. Candidate
Agricultural and Resource Economics
*   For searches and help try:
*   For searches and help try:

© Copyright 1996–2024 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index