Proc PLM is Plotting Conditional Predicted Values?

[Daisy2]

I've run a mixed model and want to plot the Actual by. Predicted values.  In JMP you can plot the predicted values or the Conditional predicted values (the values with Random Effects included) as the x-var.  I see that in Proc Mixed you have the option of saving the predicted values as OUTPRED=filename but is this using the Predicted or Conditional Predicted values?  Then, how do I graph them?  Thanks.

Or, is it better to use Proc PLM?

proc mixed data=source;
  class hyb ntrt;
  model y = a b a*b / redidual outpred=predicted;
  random hyb ntrt hyb*ntrt ;
  lsmeans a b / pdiff=all cl adjust=tukey alpha=0.10;
  title 'Model A';
  store ModA;
run;

proc plm restore=ModA;
  effectplot;
run;

[Rick_SAS · Accepted solution]

See the examples and discussion in "Visualize a mixed model that has repeated measures or random coefficients"

Briefly:

• use PROC PLM to obtain a graph of the predictions from the "marginal model" that contains the fixed effects. 
• The OUTPRED= option on the MODEL statement creates an output data set in which the predicted values incorporate random effects for each subject. Then use PROC SGPLOT to graph them, as shown in the article.

[Daisy2]

Thanks for your help with this. This is what I ended up adding:  

proc mixed data=source;
  class hyb ntrt;
  model tnc = a b a*b / residual outpred=predicted;
  random hyb ntrt hyb*ntrt ;
  lsmeans a b / pdiff=all cl adjust=tukey alpha=0.10;
  title 'Model A';
  store ModA;
run;

proc sgplot data=predicted;
  title "Predicted vs Actual Graph";
  scatter x=Pred y=tnc;
  lineparm x=0 y=0 slope=1; /** intercept, slope **/
  xaxis grid; yaxis grid;
run;