There isn't a good option here for combining the results from the JT test directly from Proc FREQ since it only reports J*.  One option might be that, since the JT statistic follows a standard normal distribution, you could hand-calculate the J and Var(J) in the formula.  Once you had those you could feed them into Proc MIANALYZE using the MODELEFFECTS and STDERR statements.  I can't think of any reason why this wouldn't be valid given the distribution, but you may want to dig a little deeper in the literature to confirm that.  ... View more

It isn't really possible to get the CL from HPLOGISTIC.  The issue is that while you can compute the point estimate for the OR which would simply be: exp(LB) where LB is b6+70.05*b7 and b6 is the estimate for age and b7 is the estimate for the interaction   you would not be able to get a standard error directly since HPLOGISTIC does not produce a table with the covariance matrix for the parameter estimates.  Without the standard error you would not be able to compute the CL.   ... View more

Because of the interaction, you will not get the odds ratios by simply exponentiating the parameter estimates.  You would need to include the continous variable set at its mean value.  You are essentially setting it at 0 by ignoring the interaction effect. This usage note might be helpful as well. https://support.sas.com/kb/24/455.html  ... View more

Technically you do not need to have the COVB= or PARMINFO= data sets in MIANALYZE unless you have a TEST statement or use the MULT option (neither of which you can use with a CLASS statement).  So I would remove them and see if it runs. proc mianalyze parms(classvar=level)=gmparms3 ; ... ... View more

I suspect that the names of the variables coming out of GLIMMIX are being truncated to 20 characters.  You can add the NAMELEN=100 option to the GLIMMIX statement to avoid this issue. https://go.documentation.sas.com/doc/en/pgmsascdc/9.4_3.4/statug/statug_glimmix_syntax01.htm#statug.glimmix.gmxoptnamelen   PROC GLIMMIX DATA = DISS3.LLCP2017_I_ANALYSIS METHOD = QUAD EMPIRICAL = CLASSICAL NAMELEN=100; ...   ... View more

All of the different imputation techniques available in SAS are listed in the link below. https://support.sas.com/kb/30/333.html#missvalue   ... View more

I think you need to sort them both by INCLUDE and _IMPUTATION_.   ... View more

Looks like you didn't sort the COVB data set the same way as the PARMS.  Try fixing that and see if the issue goes away.   ... View more

Can you post the whole LOG/code? ... View more

Rather than doing all the renaming and using the COMPRESS function, it will be easier to get them to match if you use the TRANWRD function instead.  The reason why this is necessary is because SURVEYREG names the columns in the COVB matrix using _ where the spaces are in the Parameter. Below is an example showing what I mean.   /*This assumes that the imputation has already been done*/ data farms; do _imputation_=1 to 2; do state=1 to 2; do region=1 to 3; do rep=1 to 5; farmarea=ceil(ranuni(323)*100); cornyield=.66+.95*state+.65*farmarea+rannor(3214); weight=ceil(ranuni(0)*10); output; end; end; end; end; proc surveyreg data=Farms; by _imputation_; class region; strata State ; model CornYield = region FarmArea /solution covb; weight Weight; ods output parameterestimates=parms covb=covb; run; /*Because of the way that SURVEYREG codes CLASS variables it is necessary to remove all blanks from the variable Parameter*/ data parms; set parms; parameter=tranwrd(strip(parameter),' ','_'); run; data covb; set covb; parameter=tranwrd(strip(parameter),' ','_'); run; proc mianalyze parms=parms covb=covb mult; modeleffects intercept region_1 region_2 farmarea; test region_1=region_2; run;       ... View more

One option might be to do as this page suggests, namely, treat the R-Square as you would a correlation coefficient.  This would allow you to compute a standard error using Fisher's Z transformation.  Once you do that, you could follow this example in the MIANALYZE documentation for combining correlation coefficients. ... View more