[R] Logistic regression model (Urjent help needed)

[Frank E Harrell Jr]

nitin jindal wrote:
> I am using logistic regression model (lrm) of package Design.
> 
> Can some one please tell me how to calculate the average Area Under Curve
> (AUC) for n-fold cross-validation
> 
> The help for lrm function says to do cross validation like this
> 
> f <- lrm( cy ~ x1 + x2, x=TRUE, y=TRUE)
> val <- validate.lrm(f, method="cross", B=5)

You can just say validate( . . . ) instead of validate.lrm

> 
> Now I dont know what to do with variable "val" to get the average AUC value.

Just print it and look at "index.corrected" under the Dxy row.  Somer's 
D rank correlation is related to AUC (C) by Dxy=2(C-.5)

Note that the default method of 'boot' works much better than 
cross-validation for this purpose, and both methods assume that x1 and 
x2 were the only variables or transformations examined.

Frank

> 
> thnx and regards,
> nitin
> 
> 	[[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
> and provide commented, minimal, self-contained, reproducible code.
> 


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