02-07-2018 03:03 PM
I am wondering if it is possible to fit a mixed distribution from two or more parametric families (ie gamma and normal)) within PROC FMM.
for instance the following code will not run.:
proc fmm data=catch;
class gender; model count = gender*age / dist=Normal Gamma ;
If anyone could explain if this is possible and perhaps in the case of it not being possible, why this is?
02-07-2018 05:44 PM
Read the manual. It says :
"You can specify more than one MODEL statement. Each MODEL statement identifies one or more components of a mixture. For example, if components differ in their distributions, link functions, or regressor variables, then you can use separate MODEL statements to define the components."