www.cmm.bristol.ac.uk/forum

Hi there,
I am comparing the predictive power of a range of income variables so would benefit from being able to estimate standardized beta coefficients as can be done for single-level models in stata. However I have not been successful in doing so for my multilevel models and I can't find any guidance on it in the runmlwin handbook.

I would be very grateful for any advice.

Many thanks,
Beth

Hi Beth,

I'm afraid that you can't currently ask MLwiN to report standardized beta coefficients

Note that you can't report standardized beta coefficients for multilevel models in Stata when using their own command -xtmixed- either.

You could simply standardize your response and continuous variables prior to fitting the model. This should give you the standardized beta coefficients you are after.

Else, you could calculate the standardized beta coefficients implied by the reported unstandardized beta coefficients post-estimation.

Sorry not to be of more help

Best wishes

George