approx-rand-test-0.2.0: Approximate randomization test

Stabilityexperimental
MaintainerDaniël de Kok <me@danieldk.eu>
Safe HaskellSafe-Inferred

Statistics.Test.Correction

Description

The more tests that are applied on a dataset, the more likely it becomes that a Type I error occurs (rejecting the null hypothesis when it is true). This module provides significance level corrections for repeated tests.

For more information, see:

  • Bonferroni and Šidák corrections for multiple comparisons, H. Abdi, 2007, in: N.J. Salkind (ed.), Encyclopedia of Measurement and Statistics, Thousand Oaks, CA: Sage

Synopsis

Documentation

sidakSource

Arguments

:: (Floating f, Integral i) 
=> f

Significance level

-> i

Number of comparisons

-> f

The corrected significance level

Sidak correction: α* = 1 - (1 - α)^(1 / n), where α is the intended significance level over all tests, n the number of tests, and α* the corrected significance level.

bonferroniSource

Arguments

:: (Fractional f, Integral i) 
=> f

Significance level

-> i

Number of comparisons

-> f

The corrected significance level

Bonferroni correction: α* = α / n, where α is the intended significance level over all tests, n the number of tests, and α* the corrected significance level.