Measurement error and detectable change
Translate a reliability coefficient and observed SD into SEM and individual change limits.
Your entries stay in this page’s memory and are not submitted to us. Downloads are generated locally. Reloading or leaving the page clears your entries. Do not enter patient information.
Use positive observed-score SD and reliability in [0,1). The reliability estimate must match the population, measurement protocol and intended use.
The starting values are hypothetical. Results update as you edit. Use aggregate or synthetic inputs only.
Calculation results
- Standard error of measurement
- 4.472136
- SD of two-measurement difference
- 6.3245553
- Individual MDC95
- 12.395901
How to interpret the output
Classical measurement SEM=SD×sqrt(1−reliability). Under equal independent measurement errors, MDC95=1.96×sqrt(2)×SEM describes a two-measurement individual change beyond random measurement error. It is not a minimally important clinical difference and ignores systematic bias, heteroscedasticity and reliability-estimation uncertainty.
Method referenceSource checked 2026-11-06. Read the reproducible calculator validation report.