Wednesday, January 10, 2018

Bonferroni Correction

Q: What Is the Bonferroni Correction? 

Answer: In statistical analysis, if  multiple comparisons are done (or hypotheses tested) e.g. various subgroups analysis performed in a clinical trial, the chance of a false positive result increases (Type I error) as the number of subgroup increases. The Bonferroni correction is a mathematical way to compensate for that error.

So if n is the number of hypotheses/subgroups/comparisons to obtain a desired p value of 0.05

for n=20 :: the Bonferroni correction for each individual hypothesis would be 0.05/20=0.0025

In other words, The Bonferroni correction is an adjustment made to P values when a large (dependent or independent) statistical tests are being performed simultaneously on a single data set.


Mittelhammer, Ron C.; Judge, George G.; Miller, Douglas J. (2000). Econometric Foundations. Cambridge University Press. pp. 73–74

No comments:

Post a Comment