ROCcoords {bimixt}R Documentation

ROCcoords

Description

Takes in a threshold, specificity, or sensitivity value and calculates the other two values.

Usage

  ROCcoords(model, direction = "auto", x, input)

Arguments

model

an object of type model from bimixt.model

direction

same as roc: the direction in which to make the comparison. "auto" (default): automatically define in which group the median is higher and take the direction accordingly. ">": if the values for the control group are higher than the values of the case group (controls > t >= cases). "<": if the values for the control group are lower than the values of the case group (controls < t <= cases).

x

The numeric value for the input. If input is "sensitivity" or "specificity" x must be between 0 and 1.

input

A string that defines what the input type is. Valid inputs are "sensitivity", "specificity", or "threshold". These can be shortened to "sens", "spec", "thr" or "se", "sp", "t".

Value

Returns a numeric vector with the values of threshold, specificity, and sensitivity.

Author(s)

Michelle Winerip, Garrick Wallstrom, Joshua LaBaer

See Also

coords ROCauc ROCpauc ROCplot

Examples

  cases=rmix(50,10,1.2,20,1.3,.7)
  controls=rmix(50,9,1.1,17,1.3,.95)
  model=bimixt.model(cases,controls,"4c")
  ROCcoords(model,x=.95,input="sens")
  ROCcoords(model,x=.95,input="spec")
  ROCcoords(model,x=9,input="thr")

[Package bimixt version 1.0 Index]