https://communities.sas.com/t5/Statistical-Procedures/PROC-MIANALYZE-Mantel-Fleiss-Criterion-Multiple-imputation/m-p/890744#M44170 <P>How to calculate&nbsp;Mantel-Fleiss Criterion stderr? I have&nbsp;&nbsp;Mantel-Fleiss Criterion caluclated per imputation, however I'm wondering how to pool this values into overall result via PROC MIANALYZE. Could you help?</P> Thu, 24 Aug 2023 13:02:34 GMT m491_2 2023-08-24T13:02:34Z https://communities.sas.com/t5/Statistical-Procedures/PROC-MIANALYZE-Mantel-Fleiss-Criterion-Multiple-imputation/m-p/890744#M44170 <P>How to calculate&nbsp;Mantel-Fleiss Criterion stderr? I have&nbsp;&nbsp;Mantel-Fleiss Criterion caluclated per imputation, however I'm wondering how to pool this values into overall result via PROC MIANALYZE. Could you help?</P> Thu, 24 Aug 2023 13:02:34 GMT https://communities.sas.com/t5/Statistical-Procedures/PROC-MIANALYZE-Mantel-Fleiss-Criterion-Multiple-imputation/m-p/890744#M44170 m491_2 2023-08-24T13:02:34Z https://communities.sas.com/t5/Statistical-Procedures/PROC-MIANALYZE-Mantel-Fleiss-Criterion-Multiple-imputation/m-p/891332#M44174 <P>It does not have a standard error so there is no way to compute a combined estimate.&nbsp; It would seem that such a statistic would not be very useful anyway since it is meant to test the validity of the MH approximation for the tables themselves.&nbsp; A combined estimate, even if it could be computed, would not be a way to test the combined estimate anyway.</P> <P>It might make sense in your case to simply check it for each of the imputed data sets.</P> Mon, 28 Aug 2023 14:53:11 GMT https://communities.sas.com/t5/Statistical-Procedures/PROC-MIANALYZE-Mantel-Fleiss-Criterion-Multiple-imputation/m-p/891332#M44174 SAS_Rob 2023-08-28T14:53:11Z