RecoveryResult

data class RecoveryResult(val hellinger: Double, val l1Distance: Double, val kolmogorov: Double, val numComponentsCorrect: Boolean, val familyAccuracy: Double?, val weightMeanAbsoluteError: Double?, val matching: IntArray?, val quadratureError: Double = 0.0)(source)

How well a fitted mixture recovered the mixture that generated the data.

Parameters

hellinger

the Hellinger distance between the fitted and true densities, from zero to one

l1Distance

the integrated absolute difference of the densities, from zero to two

kolmogorov

the largest absolute difference between the distribution functions

numComponentsCorrect

whether the fitted number of components equals the true number

familyAccuracy

the fraction of matched components whose family was recovered, under the equivalence rules; not defined when the component counts differ

weightMeanAbsoluteError

the mean absolute difference of matched mixing weights; not defined when the component counts differ

matching

for each true component, the index of the fitted component matched to it

quadratureError

the larger of how far the true and the fitted density integrated from the mass the grid spans; the measure's own admissibility check, since a grid that cannot represent both densities cannot measure the distance between them

Constructors

Link copied to clipboard
constructor(hellinger: Double, l1Distance: Double, kolmogorov: Double, numComponentsCorrect: Boolean, familyAccuracy: Double?, weightMeanAbsoluteError: Double?, matching: IntArray?, quadratureError: Double = 0.0)

Properties

Link copied to clipboard
Link copied to clipboard
Link copied to clipboard
Link copied to clipboard
Link copied to clipboard
Link copied to clipboard
Link copied to clipboard
Link copied to clipboard

Functions

Link copied to clipboard
open operator override fun equals(other: Any?): Boolean
Link copied to clipboard
open override fun hashCode(): Int