Stats

Statistical functions.

Installation

npm install @stdlib/stats

Usage

var statistics = require( '@stdlib/stats' );

statistics

Namespace containing statistical functions.

var stats = statistics;
// returns {...}

The namespace exposes the following statistical tests:

• anova1( x, factor[, opts] ): perform a one-way analysis of variance.
• bartlettTest( a[,b,...,k][, opts] ): compute Bartlett’s test for equal variances.
• binomialTest( x[, n][, opts] ): exact test for the success probability in a Bernoulli experiment.
• chi2gof( x, y[, ...args][, options] ): perform a chi-square goodness-of-fit test.
• chi2test( x[, options] ): perform a chi-square independence test.
• flignerTest( a[,b,...,k][, opts] ): compute the Fligner-Killeen test for equal variances.
• kruskalTest( a[,b,...,k][, opts] ): compute the Kruskal-Wallis test for equal medians.
• kstest( x, y[, ...params][, opts] ): one-sample Kolmogorov-Smirnov goodness-of-fit test.
• leveneTest( x[, y, ..., z][, opts] ): compute Levene's test for equal variances.
• pcorrtest( x, y[, opts] ): compute a Pearson product-moment correlation test between paired samples.
• ttest( x[, y][, opts] ): one-sample and paired Student's t-Test.
• ttest2( x, y[, opts] ): two-sample Student's t-Test.
• vartest( x, y[, opts] ): two-sample F-test for equal variances.
• wilcoxon( x[, y][, opts] ): one-sample and paired Wilcoxon signed rank test.
• ztest( x, sigma[, opts] ): one-sample z-Test.
• ztest2( x, y, sigmax, sigmay[, opts] ): two-sample z-Test.

In addition, it contains an assortment of functions for computing statistics incrementally as part of the incr sub-namespace and functions for computing statistics over iterators in the iterators namespace.

• incr: incremental statistics.
• iterators: statistical function iterators.

The namespace further contains functions for computing statistics on arrays as part of the array sub-namespace and functions for computing statistics on strided arrays in the strided namespace.

• array: statistical functions for arrays.
• strided: statistical operations for strided arrays.

The base sub-namespace contains lower-level statistical functions, including a dists namespace containing functions related to a wide assortment of probability distributions.

• base: base (i.e., lower-level) statistical functions.

Other statistical functions included are:

• cumax( x[, options] ): compute the cumulative maximum value along one or more ndarray dimensions.
• cumin( x[, options] ): compute the cumulative minimum value along one or more ndarray dimensions.
• kde2d(): two-dimensional kernel density estimation.
• lowess( x, y[, opts] ): locally-weighted polynomial regression via the LOWESS algorithm.
• maxBy( x[, options], clbk[, thisArg] ): compute the maximum value along one or more ndarray dimensions according to a callback function.
• max( x[, options] ): compute the maximum value along one or more ndarray dimensions.
• maxabs( x[, options] ): compute the maximum absolute value along one or more ndarray dimensions.
• maxsorted( x[, options] ): compute the maximum value along one or more sorted ndarray dimensions.
• mean( x[, options] ): compute the arithmetic mean along one or more ndarray dimensions.
• meankbn( x[, options] ): compute the arithmetic mean along one or more ndarray dimensions using an improved Kahan–Babuška algorithm.
• meankbn2( x[, options] ): compute the arithmetic mean along one or more ndarray dimensions using a second-order iterative Kahan–Babuška algorithm.
• meanors( x[, options] ): compute the arithmetic mean along one or more ndarray dimensions using ordinary recursive summation.
• meanpn( x[, options] ): compute the arithmetic mean along one or more ndarray dimensions using a two-pass error correction algorithm.
• meanpw( x[, options] ): compute the arithmetic mean along one or more ndarray dimensions using pairwise summation.
• meanwd( x[, options] ): compute the arithmetic mean along one or more ndarray dimensions using Welford's algorithm.
• mediansorted( x[, options] ): compute the median value along one or more sorted ndarray dimensions.
• midrangeBy( x[, options], clbk[, thisArg] ): compute the mid-range along one or more ndarray dimensions according to a callback function.
• midrange( x[, options] ): compute the mid-range along one or more ndarray dimensions.
• minBy( x[, options], clbk[, thisArg] ): compute the minimum value along one or more ndarray dimensions according to a callback function.
• min( x[, options] ): compute the minimum value along one or more ndarray dimensions.
• minabs( x[, options] ): compute the minimum absolute value along one or more ndarray dimensions.
• minsorted( x[, options] ): compute the minimum value along one or more sorted ndarray dimensions.
• nanmaxBy( x[, options], clbk[, thisArg] ): compute the maximum value along one or more ndarray dimensions according to a callback function, ignoring NaN values.
• nanmax( x[, options] ): compute the maximum value along one or more ndarray dimensions, ignoring NaN values.
• nanmaxabs( x[, options] ): compute the maximum absolute value along one or more ndarray dimensions, ignoring NaN values.
• nanmean( x[, options] ): compute the arithmetic mean along one or more ndarray dimensions, ignoring NaN values.
• nanmeanors( x[, options] ): compute the arithmetic mean along one or more ndarray dimensions, ignoring NaN values and using ordinary recursive summation.
• nanmeanpn( x[, options] ): compute the arithmetic mean along one or more ndarray dimensions, ignoring NaN values and using a two-pass error correction algorithm.
• nanmeanwd( x[, options] ): compute the arithmetic mean along one or more ndarray dimensions, ignoring NaN values and using Welford's algorithm.
• nanmidrangeBy( x[, options], clbk[, thisArg] ): compute the mid-range along one or more ndarray dimensions according to a callback function, ignoring NaN values.
• nanmidrange( x[, options] ): compute the mid-range along one or more ndarray dimensions, ignoring NaN values.
• nanminBy( x[, options], clbk[, thisArg] ): compute the minimum value along one or more ndarray dimensions according to a callback function, ignoring NaN values.
• nanmin( x[, options] ): compute the minimum value along one or more ndarray dimensions, ignoring NaN values.
• nanminabs( x[, options] ): compute the minimum absolute value along one or more ndarray dimensions, ignoring NaN values.
• nanrangeBy( x[, options], clbk[, thisArg] ): compute the range along one or more ndarray dimensions according to a callback function, ignoring NaN values.
• nanrange( x[, options] ): compute the range along one or more ndarray dimensions, ignoring NaN values.
• padjust( pvals, method[, comparisons] ): adjust supplied p-values for multiple comparisons.
• rangeBy( x[, options], clbk[, thisArg] ): compute the range along one or more ndarray dimensions according to a callback function.
• range( x[, options] ): compute the range along one or more ndarray dimensions.
• rangeabs( x[, options] ): compute the range of absolute values along one or more ndarray dimensions.
• ranks( arr[, opts] ): compute ranks for values of an array-like object.

Examples

var objectKeys = require( '@stdlib/utils/keys' );
var statistics = require( '@stdlib/stats' );

console.log( objectKeys( statistics ) );

Notice

This package is part of stdlib, a standard library for JavaScript and Node.js, with an emphasis on numerical and scientific computing. The library provides a collection of robust, high performance libraries for mathematics, statistics, streams, utilities, and more.

For more information on the project, filing bug reports and feature requests, and guidance on how to develop stdlib, see the main project repository.

Community

License

See LICENSE.

Copyright

Copyright © 2016-2026. The Stdlib Authors.