Class Variables in Proc Logistic

[FightingIllini]

Hey all,

I am trying to use a best subsets selection on the score chi-square for a set of both categorical and continuous predictors. The problem is that since some of my variables are categorical they have to be specified with a class statement and I can't use "selection=score" as a parameter when class variables are involved. Any ideas on how to deal with this problem? Thanks.

Here is my code:

ods output bestsubsets=score;

     proc logistic data=work.***;

     class x1 x2 x3 x4 x5 x6 x7;

     model target(event='1')= x1 x2 x3 x4 x5 x6 x7 x8 x9 x10 x11 x12 x13 x14 x15 x16 x17 x18 x19 x20 x21 x22 x23 x24 x25 x26 / selection=score best=1 start=1 stop=20;

run;

ods output close;

[StatDave]

If the CLASS variables are at least ordinal in scale and it is reasonable to assign numeric scores to their levels, then you could create numeric variables for them.  Otherwise, you might want to consider another method such as SELECTION=STEPWISE.