[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
st: RE: comparing model with gllamm
There is no question here, only a statement.
What kind of answer do you expect?
Essentially -- I guess -- you have to see how much difference
the treatment of the variable specified makes. This can be informal
as well as formal in terms of looking at whether the model
appears to perform better in one case than the other, including
how sensitive coefficients of the _other_ variables are.
In other situations, there is sometimes an argument for
including a variable both as continuous and as discrete.
But experts would need more information to comment further.
> I would like to compare between two non nested models, I am
> using gllamm
> with a continuous outcome and a mixture of discrete and continuous
> independent variables.
> Model 1: includes a variable X1 as continuous
> Model2: includes a decrete version of X1
> Thanks a lot for any help
* For searches and help try: