Dear fellow users.
Lately there was a short thread on avplot following xtreg -> doesn't work (i.e. doesn't work after any model with random effecsts). Suggestions were to regress implying fixed effects.
Any ideas on how to implement partial-regression plots (aka added-variable plot) in models with random effects?
E.g. doing it by "hand" gives predicted slopes differing from coefficients estimated in the original model.
Cheers.
Stefan
*
* 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/
