Prev: Plese help: Urgent: compare columns in 2 tables based on value from third table
Next: Running SAS on Ubuntu via wine
From: Max on 17 Apr 2010 16:07
I'm having a difficult time with something that I think should be
relatively straightforward; I want to use the regression parameters
(slope and intercept) for each patient from a repeated-measures random
effects model, but can't figure out how to output them. Using the
following model I can plot modelpreds, giving me a plot representing
the lines generated by the parameters, or using SolutionR and
SolutionF I could manually calculate the parameters for each patient.
I think MMEq and/or MMEqSol should give me the actual values used to
calculate the predictions, but I can't really make heads or tails of
them since they give me data tables with almost 200 columns named
Col1, Col2...

Is there a simple way to get the estimated slopes and intercepts of
all my patients from this model? I need it to be easy because I'll be
running 30 different models, each with a potentially different
combination of coefficients.

proc mixed mmeq mmeqsol ;
class pid ;
model y = time x time*x / solution chisq outpred=modelpreds ;
random intercept time / type=un solution subject=pid ;
ods output SolutionR = random
SolutionF = fixed
MMEq = mmeq
MMEqSol = mmeqsol ;
run ;
proc gplot data=modelpreds ;
plot pred*time / skipmiss ;
run ;
 | 
Pages: 1
Prev: Plese help: Urgent: compare columns in 2 tables based on value from third table
Next: Running SAS on Ubuntu via wine