First method:
Remove the categorical variable from the model. That will give you estimates that are weighted by the size of each class in your data.
Second method
If you want the classes to have equal weight in your estimates, you could use a variant of the adding missing values to the data technique:
data carsReg;
set sashelp.cars;
id = _n_;
output;
call missing(MSRP);
extra = 1;
do type = "Hybrid", "SUV", "Sedan", "Sports", "Truck", "Wagon";
output;
end;
keep id MSRP horsepower weight type extra;
run;
proc glm data=carsReg plots=none;
class type;
model MSRP = horsepower weight type;
output out=carsPred predicted=MSRP_pred stdp=MSRP_STDP;
run;
quit;
proc sql;
create table carsAvgType as
select
id, horsepower, weight,
mean(MSRP_pred) as MSRP_pred,
sqrt(mean(MSRP_STDP**2)) as MSRP_STDP
from carsPred
where extra
group by id, horsepower, weight;
quit;
... View more