[R] Predicting responses using ace

Frank E Harrell Jr f.harrell at vanderbilt.edu
Thu Sep 8 20:00:33 CEST 2005


Luis Pineda wrote:
> I gave a quick read to the documentation again and noticed I misinterpreted 
> it. It was print.summary.areg.boot the method I was referring to (although 
> the summary error should still work). Sorry for the inconvenience
> 
> Anyway, I used the print method on my |areg.boot| object and I got this:
> ------
> Apparent R2 on transformed Y scale: 0.798
> Bootstrap validated R2 : 0.681
> ...
> Residuals on transformed scale:
> Min 1Q Median 3Q Max
> -1.071312e+00 -2.876245e-01 -3.010081e-02 2.123566e-01 1.867036e+00
> Mean S.D.
> 1.290634e-17 4.462159e-01
> ------
> I suppose thats the R^2 evaluated using the training set, but how do I 
> evaluate the performance of the model on a uncontaminated test set?

Please read my last note.  Bootstrap validated R2 is corrected for 
overfitting and is an estimate of the likely future R2 on a totally 
independent dataset.  The bootstrap is more efficient than data 
splitting for this purpose.

Frank

> 
> 
> On 9/8/05, Luis Pineda <luisen.p at gmail.com> wrote:
> 
>>I'm trying to run the print method, but according to the documentation it 
>>needs as a parameter an object created by |summary.areg.boot| . 
>>
> 
> 
> 	[[alternative HTML version deleted]]
> 
> ______________________________________________
> R-help at stat.math.ethz.ch mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
> 


-- 
Frank E Harrell Jr   Professor and Chair           School of Medicine
                      Department of Biostatistics   Vanderbilt University




More information about the R-help mailing list