AI & Machine Learning calculator

Intraclass Correlation Coefficient (ICC) calculator

Calculate Intraclass Correlation Coefficient (ICC(1,1), ICC(2,1), ICC(3,1)) to assess inter-rater reliability for continuous numerical ratings.

Run this test live in StatLab npm i @statlab/core

When to use it

Use for assessing rating agreement when measurements are continuous numerical scores.

Required Inputs

  • Ratings matrix (N items x K raters)
  • Model type (One-way / Two-way random / Two-way mixed)
  • Unit choice (Single / Average)

Mathematical Formula

ICC = (MS_between - MS_error) / [ MS_between + (k-1)MS_error + (k/n)(MS_rater - MS_error) ]

Reporting Cautions

  • Choose ICC(2,1) for generalization to a population of raters; use ICC(3,1) when raters are fixed.
  • Average-measure ICCs are higher than single-measure ICCs.

Code Snippets (Python, R, TypeScript)

Python (SciPy / Statsmodels) 
import pingouin as pg
icc = pg.intraclass_corr(data=df, targets='item', raters='judge', ratings='score')
print(icc)
R Language 
library(psych)
ICC(matrix)
TypeScript (@statlab/core) 
import { iccCalc } from '@statlab/core';
const icc = iccCalc(matrix);

Developer Use Cases & Production Integrations

  • Assessing agreement on continuous score metrics between human evaluators and AI judges in VoxelAssurance.
  • Validating continuous quality rating consistency.

VoxelPulse Telemetry Control Plane

Continuous A/B testing, statistical telemetry analysis, and automated feedback loops for live backend services.

Explore VoxelPulse →

VoxelAssurance Release Readiness

Fixed-price AI release-readiness sprints, automated regression testing, and reliability statistical benchmarks.

Explore VoxelAssurance →

Related Statistical Test Calculators

Explore static calculators across the StatLab inference engine suite.