Hi all,
I am trying to do a multinomial logistic regression for a study with 3 categories dependent variable (SDMSCORE) and 4 categories independent variable (REGIONEW). I have used the code below. (its MEPS data .. survey based, so used surveylogistic)
proc surveylogistic data = meps.sdm;
weight poolwt;
cluster VARPSU;
strata VARSTR;
class agenew;
model SDMSCORE = regionnew / link =glogit;
run;
So in my results, it has taken a reference value in both dependent (poor) and independent(category 4) variable. IS that correct. I was thinking one of the categories in independent variable is taken as reference. the results are below:
![Screen Shot 2023-11-10 at 23.25.50.png Screen Shot 2023-11-10 at 23.25.50.png](/t5/image/serverpage/image-id/89678iF8FF0B444ADE4DD2/image-size/medium?v=v2&px=400)