Missing Value Imputation

[#1]

I published a paper in the Southeast SAS Users' Group meeting in 2021 on the topic of missing value imputation, and I am sharing it with the SAS community.

I describe the purpose of missing values, historical attempts to solve the imputation problem that missing values represent, and present a detailed analysis of census data containing missing values. I developed SAS macros to impute missing values using Fuzzy c-Means clustering, and I share my work so that others may profit from what I have created.

[Vishnu_Vivek]

Hi Team,

I've used the below code for multiple imputation. After doing imputation, I'm running multinomial logistic regression then running proc analyse. And getting only pooled/combined estimates. But I need relative estimates.

Thank you.
.
.

proc mi data=data.newdata seed=876 nimpute=5 out=outfcs;

class group sex hispan;

fcs nbiter=40 logistic (group/details);

var group sysbp01 diabp01 a1c_01 chol_01 bmi_01 sex hispan;

run;

proc logistic data = outfcs;

class group (ref = "3") sex (ref = "0") hispan (ref= "1") / param = ref;

model group = sysbp01 diabp01 a1c_01 chol_01 bmi_01 age01 sex hispan / link = glogit covb;

by _Imputation_;

ods output ParameterEstimates=lgsparms CovB=lgscovb;

run;

proc mianalyze parms (classvar=classval)=lgsparms;

class sex hispan;

modeleffects intercept sysbp01 diabp01 a1c_01 chol_01 bmi_01 age01 sex hispan ;

run;