Introduction - kstats

kstats is a Kotlin Multiplatform statistics library. It covers descriptive statistics, probability distributions, hypothesis testing, correlation and regression, and sampling — everything needed for quantitative analysis in Kotlin.

val sample = doubleArrayOf(2.0, 4.0, 4.0, 5.0, 7.0, 9.0)

val summary = sample.describe()
summary.mean              // 5.1667
summary.standardDeviation // 2.4833

val normality = shapiroWilkTest(sample)
normality.pValue          // 0.8933

val fitted = NormalDistribution(mu = summary.mean, sigma = summary.standardDeviation)
fitted.cdf(6.0)           // 0.6335

Modules

Descriptive Statistics

Mean, median, variance, quantiles, moments, frequency tables, streaming stats, and describe() summaries.

Probability Distributions

18 continuous and 10 discrete distributions with a shared API: pdf/pmf, cdf, quantile, and sampling.

Hypothesis Tests

t-tests, ANOVA, chi-squared, Fisher exact, Mann-Whitney, Wilcoxon, Shapiro-Wilk, and more.

Correlation & Regression

Pearson, Spearman, Kendall tau, partial correlation, matrices, and simple linear regression.

Sampling & Transformation

Ranking, z-score normalization, min-max scaling, binning, bootstrap, and weighted sampling.

Supported Targets

Platform	Targets
JVM	`jvm`
Android	`android`
Android Native	`androidNativeArm32`, `androidNativeArm64`, `androidNativeX86`, `androidNativeX64`
iOS	`iosX64`, `iosArm64`, `iosSimulatorArm64`
macOS	`macosArm64`
Linux	`linuxArm64`, `linuxX64`
Windows	`mingwX64`
watchOS	`watchosArm32`, `watchosArm64`, `watchosDeviceArm64`, `watchosSimulatorArm64`
tvOS	`tvosArm64`, `tvosSimulatorArm64`
JS	`js` (browser, Node.js)
Wasm	`wasmJs`, `wasmWasi`

Next Steps

Installation

Add the BOM or a single module to a Gradle KTS project.

Quick Start

Run a summary, fit a distribution, and execute a hypothesis test.

A/B Testing

Walk through a complete A/B test with assumption checks and group comparison.

​Modules