https://github.com/lukem512/levene-test
Perform Levene's statistical test for equality of group variances.
https://github.com/lukem512/levene-test
analysis deviation levene-test statistics variance
Last synced: about 1 month ago
JSON representation
Perform Levene's statistical test for equality of group variances.
- Host: GitHub
- URL: https://github.com/lukem512/levene-test
- Owner: lukem512
- Created: 2016-04-18T14:43:29.000Z (about 9 years ago)
- Default Branch: master
- Last Pushed: 2017-07-31T11:47:51.000Z (over 7 years ago)
- Last Synced: 2025-02-21T21:48:34.014Z (2 months ago)
- Topics: analysis, deviation, levene-test, statistics, variance
- Language: JavaScript
- Size: 5.86 KB
- Stars: 3
- Watchers: 3
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Levene's Test
[](https://travis-ci.org/lukem512/levene-test)  [](https://www.npmjs.com/package/levene-test) [](https://www.npmjs.com/package/levene-test) [](https://www.npmjs.com/package/levene-test)
An NPM module providing Levene's parametric statistical test. The test can be used to compute a p-value when performing [Analysis of Variance](https://www.npmjs.com/package/anova) (ANOVA). If the data you are working with is not normally-distributed it is recommended that you use the [Brown-Forsythe test](https://www.npmjs.com/package/brown-forsythe-test) instead, which uses the median rather than the mean to compute the test value.
To use it, simply install via NPM and include it in your project file.
```js
var levene = require('levene-test');
```
To compute the W-test of an array of samples use the `test` function:
```js
var samples = [[3,3,5,1], [1,2,3]];
console.log(levene.test(samples));
```
By default the test uses the absolute deviations from the group means. The quadratic (squared) deviations can also be used by specifying the `quadratic` parameter:
```js
console.log(levene.test(samples), true);
```
### License
MIT © Luke Mitchell