kstats-sampling/org.oremif.kstats.sampling

Package-level declarations

Types

data class Bin<T>(val range: ClosedRange<Double>, val items: List<T>)

A histogram bin containing the items that fall within a value range.

data class BootstrapCIResult(val percentile: ConfidenceInterval, val basic: ConfidenceInterval, val bca: ConfidenceInterval, val observedStatistic: Double, val nResamples: Int, val confidenceLevel: Double)

The result of a bootstrap confidence interval computation, containing three CI methods.

FrequencyBin

data class FrequencyBin(val range: ClosedRange<Double>, val count: Int, val relativeFrequency: Double, val cumulativeFrequency: Double)

A histogram bin with frequency statistics but without the original items.

TieMethod

enum TieMethod : Enum<TieMethod>

Controls how tied (equal) values are assigned ranks.

WeightedCoin

class WeightedCoin(val probability: Double, random: Random = Random)

A biased coin that lands heads (true) with the given probability.

WeightedDice

class WeightedDice<T>(weights: Map<T, Double>, random: Random = Random)

A weighted die that produces outcomes with probabilities proportional to their weights.

Functions

bin

fun DoubleArray.bin(binSize: Double): List<Bin<Double>>

fun Iterable<Double>.bin(binSize: Double): List<Bin<Double>>

Groups the values into equal-width bins of the given binSize.

fun DoubleArray.bin(binCount: Int): List<Bin<Double>>

fun Iterable<Double>.bin(binCount: Int): List<Bin<Double>>

Groups the values into a fixed number of equal-width bins.

binByDouble

fun <T> Iterable<T>.binByDouble(valueSelector: (T) -> Double, binCount: Int): List<Bin<T>>

Groups items into a fixed number of equal-width bins based on a numeric value extracted by valueSelector.

fun <T> Iterable<T>.binByDouble(valueSelector: (T) -> Double, binSize: Double, rangeStart: Double? = null): List<Bin<T>>

Groups items into equal-width bins based on a numeric value extracted by valueSelector.

bootstrapCI

fun bootstrapCI(data: DoubleArray, nResamples: Int, confidenceLevel: Double = 0.95, random: Random = Random, statistic: (DoubleArray) -> Double): BootstrapCIResult

Computes bootstrap confidence intervals for a statistic using three methods: percentile, basic (pivotal), and BCa (bias-corrected and accelerated).

fun <T> bootstrapCI(data: List<T>, nResamples: Int, confidenceLevel: Double = 0.95, random: Random = Random, statistic: (List<T>) -> Double): BootstrapCIResult

Computes bootstrap confidence intervals for a statistic on a list of arbitrary elements, using three methods: percentile, basic (pivotal), and BCa (bias-corrected and accelerated).

bootstrapSample