Interactive · Build v0.17

Model Explorer — Veteran Retention Logit

A hands-on walk through the validation diagnostics behind the Workforce Stability retention model. Toggle between the within-sample stratified split and the harder 2023 temporal holdout, drill into subgroup calibration, drag a threshold slider across the decision curve, and watch the four-fifths screen flip as operating points change.

ModelWeighted logit + splines + interactions
Targetretention_12mo_synthetic (modeled — illustrative)
CohortPost-9/11 vets · 22–64 · employed at interview
Updated2026-04-20
Modeled — Illustrative. The retention target is synthetic; this explorer is a methodology demo, not a prediction tool.

Calibration by subgroup

Each point is one subgroup. Horizontal axis = model's mean predicted retention for that group; vertical axis = weighted observed rate. Dots on the 45° line are perfectly calibrated. Gaps above or below are honest miscalibration — disclosed, not corrected.

Group mean-pred vs observed 45° line = perfect calibration |gap| ≥ 4 pp flagged
DimensionGroupnmean predobservedgap

Decision curve — net benefit vs threshold

Pick an operating threshold t. The chart shows model net benefit at every threshold between 0.50 and 0.90, plus the treat-all reference (the prevalence ceiling). Wherever the model's curve sits below treat-all, the model adds nothing over selecting everyone; wherever it sits above, selection is beneficial at that threshold.

0.70
Model net benefit Treat-all reference Selected threshold

Net benefit is a weighted combination of true-positive rate and false-positive rate at a given threshold, expressed in the same units as prevalence. Under a synthetic target the absolute scale should be read directionally, not as an operational guide.

Disparate-impact screen — selection rates & four-fifths rule

Pick a protected dimension and a decision threshold. Bars show the weighted selection rate (share of group predicted above threshold) per subgroup. A subgroup passes the four-fifths rule if its selection rate is at least 80% of the highest-rate group on that dimension.

Passes four-fifths (ratio ≥ 0.80) Fails four-fifths (ratio < 0.80) 80% reference line
Groupselection rateratio to maxfour-fifths

How to read this page

The three panels are not independent — they describe different faces of the same small-effect-size model. A few interpretive hooks:

Artifacts behind this page are in reports/phase6_v17/ (stratified) and reports/phase6_v17_temporal/ (temporal). Regeneration scripts: scripts/fit_retention_model_v2.py and scripts/validate_phase6_v17.py.