multinomial logistic regression

[stellapersis7]

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:

 

[SAS_Rob]

Yes, you will get n-1 sets of coefficients, where n is the number of levels to the response variable.  This is because they are restricted in a sense that the probabilities must sum to 1.  There is a good explanation as to how to interpret a generalized logit model in general in the LOGISTIC documentation.

SAS Help Center