I think it's more of a technical thing.  GLIMMIX will output results with "Odds Ratio" as the output header when a basic model is generated.   When a more complex model using the class statement is generated, GLIMMIX needs to use a different method to compute the model. The output of this method doesn't label the output in the same way as the basic one, and includes the exponential which can be interpreted as the odds ratio.  ... View more

This depends somewhat on how your data are formatted.  If the "answered/unanswered" variables are stored as 0/1, it could be just as  easy as summing the responses and using a WHERE condition:   TotalResp = A + B + C + D + E ... WHERE TotalResp = 5 Otherwise, you could compute the number of responses missing this way using the missing function. Then, exclude those for which all are blank: Total_Blank_Resp = missing( A ) + missing( B ) + missing( C ) + missing( D ) + missing( E ) ... WHERE Total_Blank_Resp = 5   ... View more

if seems because a class statement was used, the output format change due to the use of a different estimition mechanism.  The documentation for the GLIMMIX procedure clarifies that the exponentiation is the result in this case.   Here is an excerpt from the GLIMMIX Procedure description (red highlight added):   Results designated as odds or odds ratios in the GLIMMIX procedure might reduce to simple exponentiations of solutions in the "Parameter Estimates" table, but they are computed by a different mechanism if the model contains classification variables. The computations rely on general estimable functions; for the MODEL, LSMEANS, and LSMESTIMATEstatements, these functions are based on least squares means. This enables you to obtain odds ratio estimates in more complicated models that involve main effects and interactions, including interactions between continuous and classification variables.    In all cases, the results represent the exponentiation of a linear function of the fixed-effects parameters, . If and are the confidence limits for on the logit scale, confidence limits for the odds or the odds ratio are obtained as and > https://support.sas.com/documentation/cdl/en/statug/63962/HTML/default/viewer.htm#statug_glimmix_a0000001450.htm ... View more