A leverage plot is a diagnostic visualization used in regression analysis to identify data points with high leverage — observations whose predictor values are unusual or extreme relative to the rest of the data. It plots each observation's leverage value (hat value) against the observation index or against the predicted values. Leverage ranges from 0 to 1, with high-leverage points typically flagged if they exceed 2p/n (where p is the number of predictors and n is the sample size). These points can disproportionately influence the regression fit, and the leverage plot helps analysts identify them before assessing their impact on model coefficients. [formal: leverage plot | substrate: mind | horizon: a moment | explicit: yes | epoch: 0.01]
Accepted ontology entry
leverage plot
A leverage plot is a diagnostic visualization used in regression analysis to identify data points with high leverage — observations whose predictor values are unusual or extreme relative to the rest of the data. It plots each observation's…
Definition
Why it is in scope
A human-made statistical visualization: a plot that displays the leverage of each data point in a regression analysis, showing how far each predictor value lies from the center of the predictor space. Built to persist through statistical software packages and data analysis workflows.
Names and aliases
- leverage ploten · CANONICAL
Relations from this entry
- cmsk6gz0j03yknobp6dik93doINSTANCE_OF →
A leverage plot IS a specific kind of diagnostic plot — it identifies observations with high leverage in regression by plotting leverage values against observation indices. The note pins the sense correctly: a competent speaker would call a leverage plot 'a diagnostic plot'. Direction is specific→general. Leverage plots diagnose model sensitivity to individual observations.
- cmskx1k6305p8nobpedwgz05sDERIVED_FROM →
Leverage plots (also called partial residual plots) were developed within regression diagnostics to visualize the relationship between a predictor and response while controlling for other variables. Historical: came from regression methodology, not the other way around.
Relations to this entry
No accepted relations in this direction.
Record identity
- Created
- Aug 8, 2026, 9:38 AM UTC
- Content hash
- fdc1a1bcadbb8c76457b70fd1809ce0f4e3d0d170e4bb4a3021dec0a8a1fa738