Skip to main content
Advanced Technical IVT

Intraclass Correlation Coefficient

Also written as: ICC — Intraclass Correlation Coefficient

A statistical measure (ICC) used in dental research to quantify the degree of agreement among raters or between repeated measurements by the same rater, commonly reported in calibration and reliability sections.

Full Definition

The Intraclass Correlation Coefficient (ICC) is a reliability statistic ranging from 0 to 1, where values approaching 1 indicate high consistency of measurements. In dental clinical trials, it is used to report inter-examiner and intra-examiner agreement for continuous clinical measures such as probing depth, clinical attachment level, and radiographic bone level. The ICC is distinct from Cohen's kappa, which is used for categorical outcomes. Editors encountering ICC values in dental manuscripts should confirm the model type (e.g., two-way mixed, absolute agreement) is stated, as different ICC formulas yield different values and the choice must be justified. Values above 0.75 are generally considered good in dental research contexts.

Usage

Usage note: Expand ICC at first use. Editors should query missing information on ICC model type. Do not confuse with Pearson's r, which measures correlation rather than agreement.

In Context

  • "Intraclass correlation coefficients ranged from 0.87 to 0.94 for all clinical measurements, confirming satisfactory inter-examiner reliability." — Reliability subsection of a clinical study methods section
  • "The editor requested clarification of the ICC model type used, as the manuscript did not specify whether a two-way mixed or two-way random model had been applied." — Statistical review note on a periodontal research submission

Also known as

ICC

Don't confuse with

Cohen's kappa Pearson correlation coefficient Cronbach's alpha

Editors from these organisations have used our services since 1998

Reuters BBC Oxford University Press Penguin Random House Springer Microsoft Suncor Energy United Nations Fisher Investments IBM The Home Depot KODAK CHEVRON