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: Which matrix to use for continuous variables when using the xtmixed command


From   Ana Beatriz FS <[email protected]>
To   [email protected]
Subject   st: Which matrix to use for continuous variables when using the xtmixed command
Date   Wed, 19 Sep 2012 10:27:38 -0300

Dear Statalisters,

I'm performing longitudinal analysis using the command xtmixed. My
variables are all continuous and I was instructed to use the
exchangeable matrix. But the error message "could not calculate
numerical derivatives missing values encountered" always appears.
However, it doesn't happen with the other options (independent,
identity or unstructured).

Using the other options, sometimes error messages appear, depending on
the variable and on the matrix I choose. One matrix works well for
some variables but not for others. Can I use different matrices in the
bivariate analysis? Is there a preferred matrix for continuous
variables?

Best regards,

Ana Beatriz
*
*   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