Add explainers/base-rate-fallacy.md.
Why ignoring base rates makes a screening tool look useful when it is mostly wrong, and why differing base rates across groups are the statistical root of the COMPAS predictive-parity vs. equalized-odds dispute. Central to almost every fairness argument in this repo.
Suggested structure (match roc-curve-auc.md / false-positives-vs-false-negatives.md): one-sentence definition → why it matters for fairness → core concept → concrete example tied to a repo audit → runnable detection code → limitations → related concepts/projects/further reading.
Related: predictive-parity, fairness-metric-conflicts, calibration.
See CONTRIBUTING.md: add explainers/<slug>.md plus a one-line entry in assets/explainers-data.json; the build script generates the page.
Freeze-safe: explainers are fully open for contribution during the paper freeze. If you quote any Fair Code benchmark result, use the frozen numbers in paper/results-frozen/ (never re-run your own) — see CLAUDE.md.
Add
explainers/base-rate-fallacy.md.Why ignoring base rates makes a screening tool look useful when it is mostly wrong, and why differing base rates across groups are the statistical root of the COMPAS predictive-parity vs. equalized-odds dispute. Central to almost every fairness argument in this repo.
Suggested structure (match roc-curve-auc.md / false-positives-vs-false-negatives.md): one-sentence definition → why it matters for fairness → core concept → concrete example tied to a repo audit → runnable detection code → limitations → related concepts/projects/further reading.
Related: predictive-parity, fairness-metric-conflicts, calibration.
See CONTRIBUTING.md: add
explainers/<slug>.mdplus a one-line entry inassets/explainers-data.json; the build script generates the page.