NonParametric.VUS: Nonparametric estimate of volumn under ROC surface (VUS)
In DiagTest3Grp: Diagnostic test summary measures for three ordinal groups

Description Usage Arguments Details Value Note Author(s) References See Also Examples

Nonparametric estimate of volumn under ROC surface (VUS)

1	NonParametric.VUS(x, y, z,alpha=0.05,NBOOT=50,FisherZ=FALSE)

`x`	A numeric vector, a diagnostic test's measurements in the D^- (usually healthy subjects).
`y`	A numeric vector, a diagnostic test's measurements in the D^0 (usually mildly diseased subjects).
`z`	A numeric vector, a diagnostic test's measurements in the D^+ (usually severely diseased subjects).
`alpha`	A numeric value, (1-alpha)*100% percentile Confidence interval of the VUS estimate under normal assumption. Default, alpha=0.05.
`NBOOT`	A integer.Total number of bootstrap samples for implementation.
`FisherZ`	A logic value. Default=FALSE. If TRUE, will transform the nonparametric estimate through Fisher's Z transformation: θ^=1/2log(\frac{1+θ}{1-θ})*

The volume under ROC surface (VUS) indicates the probability of correctly ranking a randomly selected triplet (U,V,W) of a diagnostic test's measurements, each from D^-,D^0,D^+, i.e., VUS=Pr\{U<V<W\}. The nonparametric estimator estimates VUS by empirical CDF method, calculating the proportion of correct orderings among all possible triplets, each from three diagnosis groups.

Return a numeric value as the nonparametric estimate of the VUS.

Bug reports, malfunctioning, or suggestions for further improvements or contributions can be sent to Jingqin Luo <rosy@wubios.wustl.edu>.

Jingqin Luo

Xiong, C. and van Belle, G. and Miller, J.P. and Morris, J.C. (2006) Measuring and Estimating Diagnostic Accuracy When There Are Three Ordinal Diagnostic Groups. Statistics In Medicine 25 7 1251–1273.

Ferri, C. and Hernandez-Orallo, J. and Salido, M.A. (2003) Volume under the ROC Surface for Multi-class Problems LECTURE NOTES IN COMPUTER SCIENCE 108–120.

VUS Normal.VUS NonParametric.VUS.var

 data(AL)
 group <- AL$group
 table(group)

 ##take the negated FACTOR1 marker measurements
 factor1 <- -AL$FACTOR1

 x <- factor1[group=="D-"]
 y <- factor1[group=="D0"]
 z <- factor1[group=="D+"]

 nonpar.vus <- NonParametric.VUS(x=x,y=y,z=z)