[R] Ordered probit model -marginal effects and relative importance of each predictor-

[David Winsemius]

On Aug 27, 2011, at 3:15 PM, franco salerno wrote:

> Hi, I have a problem with the ordered probit model -polr function
> (library MASS). My independent variables are countinuos.
> I am not able to understand two main points:
>
> a) how to calculate marginal effects
> b) how to calculate the relative importance of each independent  
> variables
>
> If required i will attach my model output.

It is a great puzzle to me that people think that the output of a  
statistical program can be interpreted without a clear and complete  
description of the input.

-- 
David Winsemius, MD
West Hartford, CT