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: nlcom after two different maximum likelihood


From   Beatrice Crozza <[email protected]>
To   statalist <[email protected]>
Subject   st: nlcom after two different maximum likelihood
Date   Fri, 30 Jul 2010 13:00:34 +0100

Dear All,

I used nlcom to test a no linear combination of parameters after
maximum likelihood, to see if they are statistically different.

I did in this way, following the example in Stata help and everything is fine:

nlcom (Eq1: ( [a]_cons)*([x1]_cons)/(([a]_cons)*([x1]_cons)+(1-([x1]_cons))*[z]_cons))
(Eq2:([a]_cons)*([x2]_cons)/(([a]_cons)*([x2]_cons)+(1-([x2]_cons))*[y]_cons)),
post

test _b[Eq1] = _b[Eq2]

Now  I want to calculate nlcom for Eq1 after a particular maximum
likelihood and then, after a different maximum likelihood, Eq2 hence
do the test. I do not change the database, it is always the same for
both cases.

so, after the first maximum likelihood, I did:
nlcom (Eq1: ( [a]_cons)*([x1]_cons)/(([a]_cons)*([x1]_cons)+(1-([x1]_cons))*[z]_cons)),
post

After the second:
(Eq2:([a]_cons)*([x2]_cons)/(([a]_cons)*([x2]_cons)+(1-([x2]_cons))*[y]_cons)),
post

But when I do:

test _b[Eq1] = _b[Eq2]

I receive the error message that Eq1does not exist.

What I am doing wrong? Could you please help me?

Thank you very  much.

Best,
Bea
*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/


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