VUS.CutPoint: Find the optimal cut-points in volumn under ROC surface (VUS)...

In DiagTest3Grp: Diagnostic test summary measures for three ordinal groups

Description

Find the optimal cut-points in volumn under ROC surface (VUS) analyses which correspond to the coordinate triplet with the shortest distance to the perfect classification coordinates (1,1,1).

Usage

 VUS.CutPoint(x, y, z, cut.seq=NULL,optimize=F)

Arguments

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 D0 (usually mildly diseased subjects).
z	A numeric vector. A diagnostic test's measurements in the D+ (usually severely diseased subjects).
cut.seq	A numeric vector. A sequence of user-specified values from which the optimal cut-points will be chosen. If set to NULL, the unique collection of values of x,y,z will be used as the sequence.
optimize	A logical value of TRUE or FALSE. If FALSE, take the empirical optimal cut point identified by empirical search within the given cut.seq as final reported optimal cut point.If TRUE, using the empirical optimal cut point as starting point in optimization algorithm for final optimal cut point.

Details

The optimal cut-point t.minus, t.plus is determined based on a pair of values (t_-,t_+), t_-<=t_+, from cut.seq to minimize the goal function: (Pr(x≤ t_-)-1)^2+(Pr(t_-<y<t_+)-1)^2+(Pr(z≥ t_+)-1)^2. The probabilities are estimated by empirical CDF.

Value

Return a data frame with two columns “t.minus” and “t.plus” as optimal pair of cut-points for ROC surface analysis.

Note

Bug reports, malfunctioning, or suggestions for further improvements or contributions can be sent to Jingqin Luo <[e-mail]>.

Author(s)

Jingqin Luo

See Also

VUS Normal.VUS Youden3Grp

Examples

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

 ##take the negated kfront marker measurements
 kfront <- -AL$kfront

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

 vus.cut <- VUS.CutPoint(x=x,y=y,z=z,cut.seq=NULL)

DiagTest3Grp documentation built on April 14, 2017, 5:53 p.m.