Missing estimate outputs

[Joanna7726]

Hello, 

I am using the below syntax to retreivew estiamte values but as you can see in the output, the syntax is only estimating the last three commands and ignoring the rest of the syntax. Could anyone let me know what might be wrong with the syntax or why I am not getting outputs for the other values? Thank you very much for your help!

*0 = no stressor ; *1 = stressor;

proc mixed noclprint covtest;
 class m2id stressyn racenew gender chronic workyn marital;
 model NA =  gender C_edu racenew C_age Z_N_hhinc chronic C_N_neuro workyn marital C_PA m_stress C_lifedis|stressyn C_daydis|stressyn
/solution CL ddfm=bw;
   random intercept stressyn /subject=m2id;

estimate 'Estimate of outcome variable for non-stressor days in -1SD Discrimination' intercept 1 stressyn 0 C_daydis*stressyn -4.7007771;
estimate 'Estimate of outcome variable for non-stressor days in Mean Discrimination' intercept 1 stressyn 0 C_daydis*stressyn 1;
estimate 'Estimate of outcome variable for non-stressor days in +1SD Discrimination' intercept 1 stressyn 0 C_daydis*stressyn 4.7007771;
estimate 'Estimate of outcome variable for stressor days in -1SD Discrimination'     intercept 1 stressyn 1 C_daydis*stressyn -4.7007771;
estimate 'Estimate of outcome variable for stressor days in Mean Discrimination'     intercept 1 stressyn 1 C_daydis*stressyn 1;
estimate 'Estimate of outcome variable for stressor days in +1SD Discrimination'     intercept 1 stressyn 1 C_daydis*stressyn 4.7007771;

estimate '-1SD Discrimination Effect for Non-Stressor Days' C_daydis -4.7007771 C_daydis*stressyn 0/cl;
estimate 'Mean Discrimination Effect for Non-Stressor Days' C_daydis 1 C_daydis*stressyn 0/cl;
estimate '+1SD Discrimination Effect for Non-Stressor Day'  C_daydis 4.7007771 C_daydis*stressyn 0/cl;
estimate '-1SD Discrimination Effect for Stressor Day'      C_daydis -4.7007771 C_daydis*stressyn -4.7007771/cl;
estimate 'Mean Discrimination Effect for Stressor Day'      C_daydis 1 C_daydis*stressyn 1/cl;
estimate '+1SD Discrimination Effect for Stressor Day'      C_daydis 4.7007771  C_daydis*stressyn 4.7007771/cl;
run;

[PaigeMiller]

Non-est means you can't estimate this from the model fit. Sometimes this happens because you have interactions in the model, but there are empty cells i.e. combination of variables in an interaction such as C_lifedis*stressyn (or any other interaction in the model) has at least one empty cell.

Also, to get predicted values and confidence intervals at a particular set of x-values is via these methods. The ESTIMATE statement is not the way to do it.

https://blogs.sas.com/content/iml/2014/02/17/the-missing-value-trick-for-scoring-a-regression-model....

https://blogs.sas.com/content/iml/2014/02/19/scoring-a-regression-model-in-sas.html