Bland-Altman limits of agreement

Computes Bland-Altman limits of agreement between two measurement methods.

Open the calculator → Runs in your browser. Data leaves only if you deliberately send a problem report from the interactive tool.

Example

Mean of the differences, in the units measured
-0.4
Standard deviation of the differences
1.2
Number of paired measurements
85

Result: limits of agreement spanning about 4.7, each with its own interval

The tool opens with these values already filled in. Replace them with your own.

What the result means

Bias
The mean of the differences. Its sign says which method reads higher, and a bias can be corrected for.
The limits
Bias plus and minus 1.96 standard deviations of the differences. 95% of future differences are expected between them.
Correlation
Not agreement. Two methods can correlate almost perfectly and disagree by a clinically enormous margin.
Acceptability
A clinical decision, and one the papers say should be set before the study rather than read off the result.
Uncertainty
Each limit is itself an estimate, with a standard error of about the standard deviation times the square root of 3 over the number of pairs.
A caution
If the difference varies with the size of the measurement, one pair of limits is the wrong summary and only the plot shows it.

What you enter

  • Mean of the differences, in the units measured
  • Standard deviation of the differences
  • Number of paired measurements
How this is calculated

Bland JM, Altman DG. Statistical methods for assessing agreement between two methods of clinical measurement. Lancet. 1986;1(8476):307-310. Bland JM, Altman DG. Measuring agreement in method comparison studies. Stat Methods Med Res. 1999;8(2):135-160. Read the source ↗

A reference and educational tool. Not medical, legal, or financial advice, and not a substitute for clinician judgment.

Browse all tools

Built by Clay Good. Source on GitHub.