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

Re: st: ml check shows errors but ml maximize works

From   [email protected] (Jeff Pitblado, StataCorp LP)
To   [email protected], Alita Nandi <[email protected]>
Subject   Re: st: ml check shows errors but ml maximize works
Date   Thu, 26 May 2005 10:20:27 -0500

Alita Nandi <[email protected]> is getting an error message from
-ml check- when -ml max- would otherwise produce estimation results:

> --ml check-- gives the error message "cannot find feasible values" when it 
> is testing to see whether the likelihood evaluator (the program that I have 
> written to calculate the log-likelihood) works or not. But when I run --ml 
> maximize-- without running --ml check-- before it, the maximization works 
> and I get the estimates. By using --ml search-- before --ml maximize-- I 
> get the same estimates. What I want to know is whether it is possible for 
> --ml check-- to show that there are problems with my likelihood evaluator 
> even if there is none. If not, what kind of errors in my programming (or 
> perhaps the data set) may cause this discrepancy? I have not written the 
> program code in this email so as not to clutter it. But please let me know 
> if it is necessary to see the program code in order to be able to provide 
> answers to my questions and I will do so.
> I am running Intercooled STATA Version 8 on Windows.

We are confident that the results from -ml max- are reasonable; however, we
are unable to reproduce the problem with -ml check- that Alita mentions.

If Alita will send me the likelihood evaluator and a dataset with a log that
show the steps that result in the error message, we will look into this and
report on what we find.

[email protected]
*   For searches and help try:

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