Paola Di Stefano wrote:
I need to translate this procedure from SAS to Stata:
proc mixed;
class numero;
model bnp=dte / noint s;
repeated / subject=numero r;
run;
--------------------------------------------------------------------------------
Here's a stab at it:
xtmixed bnp dte, noconstant || numero:
dte's absence from the CLASS statement indicates that it's continuous. (It
seems odd not to want an intercept in such a model.) I believe the default
variance-covariance structure for the REPEATED statement is variance
components, so dte won't appear in the random effects equation as a random
slope.
Joseph Coveney
*
* 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/
