intraklassekorrelasjon

Intraklassekorrelasjon, often abbreviated as ICC, is a statistical measure used to assess the reliability or consistency of measurements made by different observers or within the same observer across different occasions. It quantifies the degree of agreement among a set of measurements that are expected to be measuring the same underlying construct. The ICC can range from 0 to 1, where a value of 1 indicates perfect agreement and a value of 0 indicates no agreement beyond what would be expected by chance.

The calculation of ICC typically involves an analysis of variance (ANOVA) framework. It essentially partitions the total variance observed in the data into components attributable to the differences between the subjects being measured and the variance arising from agreement among the raters or measurements. Different forms of ICC exist, distinguished by the specific model assumptions they employ regarding the raters (e.g., whether raters are fixed or random) and the nature of the measurements (e.g., absolute agreement versus consistency).

ICC is widely used in various fields, including psychology, medicine, and education, to evaluate the reliability of diagnostic tests, observer ratings, and repeated measurements. A high ICC value suggests that the measurements are reliable and can be trusted to reflect true differences or states. Conversely, a low ICC value indicates poor agreement, suggesting issues with the measurement instrument, the training of observers, or the clarity of the assessment criteria. Understanding the specific ICC form and its interpretation is crucial for drawing valid conclusions about measurement reliability.