My code:
/*FULL MODEL KP cases and KP controls*/
proc logistic data=paul.mi_20_paul; where table3b ne .;
class cc16_ngperml90 (ref='0') Ab_titre_mcg_ml2(ref='0') CRP_ng_ml90(ref='0')cc16_ngperml90(ref='0')
sST2R_ngperml90(ref='0')FEV_FVC_80 (ref='0') KL6_Conc_U_ml90(ref='0') Highmold (ref='0')/param=ref;
model cases (event='1')=AvgNo4No7 alvno FEV_FVC_80 Ab_titre_mcg_ml2 Highmold KL6_Conc_U_ml90 CRP_ng_ml90
cc16_ngperml90 sST2R_ngperml90 / covb expb;
by _imputation_;
ods output parameterestimates = model_1imp covb = covmat1;
run;
*combine results into a data set of parameter estimates, standard errors and so on;
proc mianalyze parms(classvar=classval) = model_1imp ;
class ;
modeleffects AvgNo4No7 alvno FEV_FVC_80 Ab_titre_mcg_ml2 Highmold KL6_Conc_U_ml90 CRP_ng_ml90
cc16_ngperml90 sST2R_ngperml90;
ods output parameterestimates = comb_final ;
run;
data logout_a;
set comb_final;
if parm ^="intercept";
odds_ratio = exp(estimate);
odds_LCLMean = exp(lclmean);
odds_UCLMean = exp(uclmean);
run;
proc print data = logout_a noobs;
var parm odds:;
run;
This thread seems similar to what you're working on. Would it work for you as well, to use PROC FREQ by _IMPUTATION_ and letting that chi-square propagate through the PROC MI and PROC MIANALYZE you already have working?
Don't miss out on SAS Innovate - Register now for the FREE Livestream!
Can't make it to Vegas? No problem! Watch our general sessions LIVE or on-demand starting April 17th. Hear from SAS execs, best-selling author Adam Grant, Hot Ones host Sean Evans, top tech journalist Kara Swisher, AI expert Cassie Kozyrkov, and the mind-blowing dance crew iLuminate! Plus, get access to over 20 breakout sessions.
Learn how use the CAT functions in SAS to join values from multiple variables into a single value.
Find more tutorials on the SAS Users YouTube channel.