> Dear All:
> I am calculating the relative importance of a regressor in a linear
> Does anyone know how I can obtain/install the 'pmvd' computation type? I
> a US user.
Do you have any specific reason to use the "pmvd" method, especially in
the light of
The default "lmg" method
- gives very similar results,
- is more well-known in the literature, and
- is included in the US-version of the package.
Anyway, as a non-US user once upon a time I tried both methods, and they
really did not deviate that much (at least the ordering of the variables
was highly similar).