st: simple slopes after xtmixed

[Jordan Silberman <silberman.stata@gmail.com>]

Two questions on computing simple slopes after xtmixed:

1. Some have suggested that, after xtmixed, you can compute simple slopes using either the lincom post-estimation command or the margins post-estimation command. Alternatively, to probe simple slopes for mixed effects models, Preacher created an online calculator tool (http://quantpsy.org/interact/hlm2.htm). Can anyone tell me if the Preacher approach to computing simple slopes for mixed effects models is the same as and/or is comparable to either lincom or the margins command? 

2. Using the lincom and margins commands after xtmixed to compute simple slopes yields different results. Why?

Any guidance would be greatly appreciated.
Jordan
*
*   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/