ddensity: Double probability density computation and plotting

In davidavdav/ROC: Compute structures to compute ROC and DET plots and metrics for 2-class classifiers.

Double probability density computation and plotting

Description

ddensity computes the density of the scores in a cst data frame simultaneously for target and non-target scores. The main purpose is for plotting the densities of the scores.

Usage

 ddensity(x, ...)
 plot(ddensity(x))

Arguments

x	An object of class cst, or a data frame that can be coerced into that
...	Additional arguments for density

Details

plot.ddensity draws two probability density curves based on the data in the ‘collection of supervised trials’ (cst) data frame, scaling the x- and y-axes to cover the ranges of both the target and non-target distributions. The two distributions are drawn in blue and red, with their label near the mode of the distribution.

This gives a quick impression on how the scores of the ROC analysis are distributed with respect to each other.

Author(s)

David A. van Leeuwen

Examples

## data from TNO's submission to NIST Speaker Recogntion Evaluation 2008
data(tno.2008)
plot(ddensity(tno.2008))

davidavdav/ROC documentation built on Sept. 8, 2023, 2:39 p.m.