The item store in PROC REG will only generate the predicted observations and not intervals in the PLM procedure.  The item store from PROC REG only stores the parameter estimates so only a subset options are available.  If you have a continuous response use the GLM procedure to estimate the model and then PLM procedure to obtain predicted observations and intervals for the new data set.  For example,   /* SAS CODE FOLLOWS */ data fitness;       input age weight oxygen runtime restpulse runpulse maxpulse;       datalines;    44 89.47  44.609 11.37 62 178 182    40 75.07  45.313 10.07 62 185 185    44 85.84  54.297  8.65 45 156 168    42 68.15  59.571  8.17 40 166 172    38 89.02  49.874  9.22 55 178 180    47 77.45  44.811 11.63 58 176 176    40 75.98  45.681 11.95 70 176 180    43 81.19  49.091 10.85 64 162 170    44 81.42  39.442 13.08 63 174 176    38 81.87  60.055  8.63 48 170 186    44 73.03  50.541 10.13 45 168 168    45 87.66  37.388 14.03 56 186 192    45 66.45  44.754 11.12 51 176 176    47 79.15  47.273 10.60 47 162 164    54 83.12  51.855 10.33 50 166 170    49 81.42  49.156  8.95 44 180 185    51 69.63  40.836 10.95 57 168 172    51 77.91  46.672 10.00 48 162 168    48 91.63  46.774 10.25 48 162 164    49 73.37  50.388 10.08 67 168 168    57 73.37  39.407 12.63 58 174 176    54 79.38  46.080 11.17 62 156 165    52 76.32  45.441  9.63 48 164 166    50 70.87  54.625  8.92 48 146 155    ;   run;   data new; input age weight oxygen runtime restpulse runpulse maxpulse; datalines;    51 67.25  45.118 11.08 48 172 172    54 91.63  39.203 12.88 44 168 172    51 73.71  45.790 10.47 59 186 188    57 59.08  50.545  9.93 49 148 155    49 76.32  48.673  9.40 56 186 188    48 61.24  47.920 11.50 52 170 176    52 82.78  47.467 10.50 53 170 172    ;   run;  proc glm data=fitness;       model Oxygen=Age Weight RunTime RunPulse RestPulse MaxPulse;      store glmres; quit;   proc plm restore=glmres;  score data=new out=newout predicted=predoxy lcl=lcl ucl=ucl lclm=lclm uclm=uclm;  quit; ... View more

I have been able to replicate the behavior of zero coefficient included in the final model using LASSO selection. In my statistical opinion, if the zero coefficients appear in the intermediate steps, it would be quite reasonable and okay. However, there should be no zero coefficients in the final selected model.   I have informed our developers of this particular behavior and we are currently researching this particular issue. I will update you once I have more specific details.    ... View more

If you have not suppressed the ODS Graphics you might try that to see if that makes any difference.  For example prior to your PROC TTEST statement specify the following statement:    ODS GRAPHICS OFF;   You may want to open a track and contact SAS Technical Support to determine why your TTEST is not creating the ODS OUTPUT data sets.  https://support.sas.com/en/technical-support/contact-sas.html   ... View more

Please keep in mind each data set and model should be evaluated independently. Here are a few suggestions to try when you encounter the fail to converge message in the SAS LOG when using PROC GLIMMIX:   You can try some of the NLOPTIONS when you have convergence problems. For example,     NLOPTIONS TECHNIQUE=NRRIDG; or NLOPTIONS TECH=NEWRAP; and see if that helps your model to converge.  Using NLOPTIONS=NRRIDG; for Binary, Binomial, Poisson, NegBin seems to help convergence.    If your variables or parameter estimates are of wildly different scales (like .0001 vs 100) then you may need to rescale your data or your model.   Try different starting values for your random effects by adding a PARMS statement.     You can also try adding the INITGLM option to the PROC GLIMIMX statement.   Examine the iteration history, does it look like it is making progress toward convergence. At the end (19 + 1initial optimizations is the default) if you are oh-so-close but do not quite make the convergence criteria. I would suggest that you  increase the MAXOPT= in the PROC statement to 50 to see if your model converges. You can also increase the MAXITER= option on the NLOPTIONS statement to increase the number of iterations.   Try different METHODs= Laplace etc  on PROC GLIMMIX statement such as METHOD=LAPLACE or QUAD if you are using SAS 9.2 or later for conditional model.   You may have to reconsider your model and simplify it.  You may have to use simpler TYPE= structure as in your example TYPE=VC rather than TYPE=UN or you may have to reconsider the fixed effects. ... View more