I really appreciate your advice! ... View more

I would say that there is really no fair way to compare the two models as they are now.  PHREG is fitting a competing risks model with a very different likelihood function than GLIMMIX would fit (treating the response as having a normal LL by default). This section of the documentation might be helpful in understanding some of the differences. SAS Help Center: Analysis of Competing-Risks Data ... View more

I appreciate the clarification. The assignment this is to produce a figure for our primary model. The material hasn’t really covered the differences between the different confidence interval estimates. I’m primarily interested in creating a figure of some sort, but I am having trouble finding the graphics options for SURVEYLOGISTIC. ... View more

Thanks so much for the help, I really appreciate it. This worked perfectly and completely fixed my issue!!! ... View more

You either have to impute values to replace the missings (probably not advisable when it seems like 99% of the data is missing) or remove the variable from the model. ... View more

The link given to the %COMBCHI macro is not being updated and still points to v1.0. There is an amended formula in version 2.1 of  Dr. Paul Allison's %COMBCHI macro from 2007 linked from the "Resources" section of his bio at https://statisticalhorizons.com/our-instructors/paul-allison/ ... View more

I think it depends on what you want to assume about the missing values in the variables that you do not want to impute.  Are they missing at random, MNAR or actually valid responses? ... View more

That worked, thank you! ... View more

Thanks! ... View more

The message you are receiving can have a number of possible causes.  The first is that there is some problem with the imputation model itself (I have seen where people have left the response variable off the VAR statement in Proc MI as an example).  In general though, it occurs when the missing data has no influence on the sampling error of a parameter estimate.  There is no fix or adjustment for that, but it does require some further investigation on your part.  Usually, it is an indication of a problem with the imputation model with possible causes ranging from a poor imputation model to no real need to impute due to a very small fraction of missing information.     Without fixing the problem, when the between imputation variance is zero then the number of Degrees of Freedom is undefined so you cannot get a confidence interval or p-values.  If you are unable to determine the cause then one suggestion would be that, if there are only minimum differences among these within-imputation variances, then look at the results for that variable for one of the imputations.   ... View more

It looks like you have added variables to the CLASS statement in MIANALYZE that are not CLASS variables in the actual model (like year_diagnosis).  When I fix that, the MIANALYZE step runs without any errors.   PROC MIANALYZE parms(classvar=level)=gm_fcs; class race_collapsed sexuality_dich smoking alcohol_use rural income2 employment2 education2 breastfeed; MODELEFFECTS INTERCEPT race_collapsed BMI sexuality_dich age2 agediagnosed diagnosticdelay income2 employment2 education2 smoking alcohol_use rural age_firstperiod preg3 breastfeed num_comorbidities year_diagnosis; run;   ... View more

@SAS_Rob Thank you for the link. This worked perfectly. ... View more

Thank you so much. It worked. ... View more

Thank you for the quick and informative response! While I am familiar with the model selection selection techniques in proc logistic, please correct me if I am wrong, these methods are primarily used for unconditional logistic regression and not applicable for conditional? Thank you -    ... View more