Intra Class Correlation Calculator (ICC)

If you want to calculate an intraclass correlation (ICC) just select more than 3 metric variables, then an intraclass correlation will be calculated automatically online.

Calculate intra class correlation

The intraclass correlation, or ICC for short, is a measure of the agreement between more than two dependent observations, i.e. observations on the same cases. An intraclass correlation of 0 means that there is no agreement at all and an intraclass correlation of 1 means that there is a complete agreement. To calculate an intraclass correlation, an analysis of variance is calculated, comparing the variance between cases and within cases.

The intraclass correlation (ICC) thus assesses the reliability of ratings by comparing the variability of different raters of the same case with the total variation across all raters and n cases.

What is Intra Class Correlation?

Intra-class correlation (ICC) is a statistical measure that quantifies the degree of similarity or consistency among observations that are made on the same individuals or objects. ICC is used to assess the reliability and consistency of measurements taken by different raters, assessors, or instruments.

There are several types of ICC, each designed for a specific type of data and research design. The most commonly used types of ICC are:

• Single measure ICC: used when a single measurement is taken on each subject or object. This type of ICC is also known as the consistency ICC.
• Two-way random effect ICC: used when multiple measurements are taken on each subject or object, and there are multiple raters or assessors. This type of ICC is also known as the agreement ICC.
• Two-way mixed effect ICC: used when multiple measurements are taken on each subject or object, and there are both multiple raters or assessors and multiple subjects or objects. This type of ICC is also known as the average measure ICC.

The ICC values can range from 0 to 1, with 1 indicating perfect agreement or consistency among the observations, and 0 indicating no agreement or consistency. The interpretation of ICC values depends on the type of data and research design, but generally, ICC values above 0.75 are considered to be good, and values above 0.9 are considered to be excellent.

In conclusion, ICC is a useful measure for assessing the reliability and consistency of measurements taken by different raters, assessors, or instruments. It is widely used in various fields such as medicine, psychology, and education. Different types of ICC are used for different types of data and research designs, and the interpretation of ICC values depends on the context. It is always recommended to report the type of ICC used, the ICC value, and the sample size used to calculate the ICC.