Bonferroni Correction
Definition
A standard adjustment for multiple comparisons: the significance threshold for any individual test is divided by the total number of tests performed, so that the family-wise error rate remains at the desired level. Applicable in forensic contexts where multiple independent features are tested.
- Purpose
- Adjusts significance threshold for multiple comparisons
- Method
- Divide the chosen alpha by the number of tests performed
- Controls
- Family-wise error rate across all tests
- Trade-off
- Reduces false positives but lowers power to detect true effects
Common questions
Why does testing multiple features without correction inflate the risk of a false match?+
Each individual test carries its own chance of a false positive, and running many tests on the same data compounds that chance across the whole set. Without adjusting the threshold, a feature comparison may appear statistically significant purely by running enough tests, not because a genuine association exists.
Is the Bonferroni correction the only method used to control this problem?+
No, it is the simplest and most conservative option. Other methods, such as the Holm-Bonferroni step-down procedure or false discovery rate control, achieve similar protection with less loss of statistical power, and are sometimes preferred when many comparisons are tested.
Related terms
- Base Rate
- The prior probability of an event or proposition before specific evidence is considered. In forensic inference, the base rate is the probability...
- Database Match Probability
- The adjusted probability that a coincidental match to a crime-scene profile exists somewhere in a database, accounting for the number of profiles...
- Ecological Fallacy
- The error of applying a statistical association observed at the population or group level to an individual, without verifying that the individual...
- Look-Elsewhere Effect
- The inflated apparent significance of a finding that arises when many features, tests, or subsets are examined and only the significant result...
- Multiple Comparisons Problem
- The inflation of the probability of at least one false-positive result that occurs when many statistical tests or pairwise comparisons are made....