[R] linear predicted values of the index function in an ordered probit model

[David Winsemius]

On Jun 28, 2010, at 10:58 AM, Martin Spindler wrote:

> Hello,
>
>
>
> currently I am estimating an ordered probit model with the function  
> polr
> (MASS package).
>
> Is there a simple way to obtain values for the prediction of the index
> function ($X*\hat{\beta}$)?
>
> (E..g. in the GLM function there is  the linear.prediction value for  
> this
> purpose).

Read the help page:

"There are methods for the standard model-fitting functions, including  
predict, ...."
>
>
>
> If not, is there another function / package where this feature is
> implemented?

Even though polr has predict, you can also get a proportional odds  
model in the rms package (and I would not be surprised if a search  
turned up more options.

-- 
David.
>
>
>
> Thank you very much for your answer in advance!
>
>
>
> Best,
>
>
>
> Martin
>
>
> 	[[alternative HTML version deleted]]
>
> ______________________________________________
> R-help at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.

David Winsemius, MD
West Hartford, CT