Saved Search

Reliability & Agreement · ICC-1S

Sample Size for Hypothesis Test of Intraclass Correlation Coefficient

Plan the number of subjects needed for a one-sided test of intraclass correlation coefficient reliability.

1. Information obtained from previous studies or literature

Use a defensible minimum acceptable ICC from prior evidence or the protocol.

2. Information decided by the researcher

The one-sided method requires the expected ICC to exceed the minimum acceptable ICC.

Defaults to 10%. Enter 0 if no adjustment is required.

3. Results

Enter the planning assumptions and select Calculate.

Formula, assumptions, limitations, and methodological note

Example clinical scenario

Several radiologists score the same chest images, and the researcher wants to test whether the intraclass correlation coefficient exceeds the minimum acceptable reliability.

Formula and methodological note

This calculator uses the preserved published approximation documented in the calculator specification. It assumes the selected reliability or agreement model, independent subjects, the stated number of items or ratings, and defensible planning values.

Sample size is rounded upward before the dropout/non-response adjustment, which is also rounded upward. The method does not replace design-specific review for clustered samples, multiple raters beyond the stated model, missing ratings, weighted kappa, ordinal outcomes, or alternative ICC definitions.

Method references

  1. Bonett DG. Sample size requirements for estimating intraclass correlations with desired precision. Stat Med. 2002;21(9):1331–1335.
  2. Walter SD, Eliasziw M, Donner A. Sample size and optimal designs for reliability studies. Stat Med. 1998;17(1):101–110.

Suggested citation

Yaacob, Najib Majdi. “Sample Size for Hypothesis Test of Intraclass Correlation Coefficient (ICC-1S).” Web calculator. NajibMY, 2026. Accessed July 29, 2026. http://127.0.0.1:4321/tools/sample-size/reliability-agreement/intraclass-correlation-coefficient/.