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]

Re: st: understanding ml (and its failure)


From   Nick Cox <njcoxstata@gmail.com>
To   "statalist@hsphsun2.harvard.edu" <statalist@hsphsun2.harvard.edu>
Subject   Re: st: understanding ml (and its failure)
Date   Thu, 10 Oct 2013 17:34:49 +0100

I stop at reading that you have variables B1 and B2 which are in
practice constants. A constant can have no relationship with a
response and thus no predictive value. Regardless of how you view such
variables substantively or theoretically there is no point in trying
to use such variables in a model.

By the way, please honour the request to use full real names on Statalist.
Nick
njcoxstata@gmail.com


On 10 October 2013 17:26,  <altruist81@gmx.de> wrote:
> Dear Statalisters,
> I am trying to understand a do file where the underlying data has the variables B1 and B2 which are both equal to 0 for all observations. After the programm -mlblub- is defined, it is used in the -ml- framework in the following way: -ml model lf mlblub (A1: B1=one, nocons) (A2: B2=one, nocons), maximize search(off) difficult trace init(2 1, copy) technique(dfp)-
> I have two directly related questions.
> 1. What is the function of the B1=one and B2=one terms in the equation?
> 2. If I run the the -ml- line I get the error message "initial values not feasible" r(1400). Is that because of the 0 values in B1 and B2?
> Best,
> Darjusch
> *
> *   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/

*
*   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