Bonferroni correction

Statistics. Statistical adjustment for the multiple testing when several statistical tests are performed simultaneously. In order to avoid a lot of false positives (type 1 error), the significance level (alpha value) needs to be lowered to account for the number of comparisons being performed because a given alpha value may be appropriate for each individual comparison, but not for the set of all comparisons. For example, if 100 tests at the alpha value 0.05 are performed, there will be 5 p values of less than 0.05 by chance which lead to false positive results. Bonferroni correction sets the alpha value for the entire set of n comparisons equal to alpha by taking the alpha value for each comparison equal to alpha/n (e.g., alpha = 0.05/100 = 0.0005).

Search for publications that include this term →