st: Re: scalars versus temporary variables in MLE

[Kit Baum <baum@bc.edu>]

In addition to Nick's excellent diagnosis and advice, I would add the  
following. You don't need to do more than one iteration to see that  
the two programmes you have provided differ in their logic. If they  
truly were the same, they would return the same value of the  
loglikelihood function when first called, which they clearly do not.  
If you rewrite a program in what you imagine is an innocuous way and  
you get a different LLF on first evaluation, you have changed the  
program.

Kit Baum, Boston College Economics
http://ideas.repec.org/e/pba1.html


On Jun 21, 2006, at 2:33 AM, Deepankar wrote:


> I provide both the programs (FIRST PROGRAM has temporary variables;  
> SECOND PROGRAM has scalars) and output from running them below;  
> probably someone can throw some light on this perplexing issue.
*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/