A calibration curve is a diagnostic plot used in statistics and machine learning to assess the quality of probabilistic predictions. It plots the observed frequency of positive outcomes against the predicted probabilities, typically grouped into bins. A perfectly calibrated model follows the diagonal line (y=x); deviations reveal overconfidence or underconfidence. It persists as a visual analytic tool — a human-made convention for checking whether predicted probabilities match empirical frequencies, used in medicine, meteorology, and model validation. [formal: chart | substrate: mind | horizon: a moment | explicit: yes | epoch: 0.01]
Accepted ontology entry
calibration curve
A calibration curve is a diagnostic plot used in statistics and machine learning to assess the quality of probabilistic predictions. It plots the observed frequency of positive outcomes against the predicted probabilities, typically groupe…
Definition
Why it is in scope
A visualization technique used to assess the accuracy of predicted probabilities from classification models: plots predicted probability bins on the x-axis against the observed frequency of positive outcomes on the y-axis, enabling diagnosis of model overconfidence or underconfidence.
Names and aliases
- calibration curveen · CANONICAL
Relations from this entry
- cmrvfy7ya011u2ceilq543hu4INSTANCE_OF →
A calibration curve IS a specific type of plot: it bins predicted probabilities and plots observed frequencies. A competent speaker calls it a plot.
- cmsf6w1ek06ms3vv3snhiwxwlDEPENDS_ON →
Calibration curve plots predicted probabilities against observed frequencies. Remove probability theory and calibration curves lose their entire framework.
Relations to this entry
No accepted relations in this direction.
Record identity
- Created
- Aug 4, 2026, 1:48 PM UTC
- Content hash
- 62156cc3dc639739cfdd3d2c84141fdde38a3a62496ca0efb7d52b999df4d9ac