Hello. I am conducting mi procedure. My outcome is 3 variables. I used fcs logistic.    step 1/* Impute missing data using logistic regression */ proc mi data=mydata_mental seed=12345 nimpute=20 out=outfcs_impute; where _age_g=6; class ment14d_w fall12mn_w _sex  age65plus_w urbstat_w  educag_w  racegr4_w income_w marital_w hlthpl1_w   persdoc3_w  medcost1_w checkup1_w  exerany2_w; fcs logistic (ment14d_w/details) logistic (income_w) ; var ment14d_w fall12mn_w  _sex  age65plus_w urbstat_w  educag_w  racegr4_w marital_w hlthpl1_w   persdoc3_w  medcost1_w checkup1_w  exerany2_w _ststr _psu _llcpwt income_w; run;   step 2 /* Analyze each imputed dataset using logistic regression */ This works ******** proc logistic data = outfcs_impute; Class ment14d_w (ref="0") fall12mn_w (ref="0") _sex (ref="1")  age65plus_w (ref="1") urbstat_w(ref="1") educag_w (ref="1")  racegr4_w(ref="1") income_w(ref="1") marital_w(ref="1") hlthpl1_w(ref="0")   persdoc3_w(ref="0")  medcost1_w(ref="0")  checkup1_w(ref="0")   exerany2_w(ref="0")/param=ref; model ment14d_w = fall12mn_w _sex  age65plus_w urbstat_w  educag_w  racegr4_w income_w marital_w hlthpl1_w   persdoc3_w  medcost1_w checkup1_w  exerany2_w / link = glogit covb; by _imputation_; ods output ParameterEstimates=lgsparms CovB=lgscovb; run; /* Pool results across imputed datasets */ (this works  but I do not get coefficient for (3 categories for dependent var) proc mianalyze parms(classvar=classval)=lgsparms; class ment14d_w fall12mn_w  _sex  age65plus_w urbstat_w  educag_w  racegr4_w income_w marital_w hlthpl1_w   persdoc3_w  medcost1_w checkup1_w  exerany2_w; modeleffects intercept ment14d_w  fall12mn_w  _sex  age65plus_w urbstat_w  educag_w  racegr4_w income_w marital_w hlthpl1_w   persdoc3_w  medcost1_w checkup1_w  exerany2_w; run; My questions.  How can I get odds ratio (in simple step) in pooled results after mianalyze? How can I get coefficient value for final output after mianalyze? ... View more