Glossary · Sensors and measurement
Measurement uncertainty
Also known as: Uncertainty of measurement
German: Messunsicherheit
In metrology, measurement uncertainty is a non-negative parameter that characterizes the dispersion of the values reasonably attributed to the measurand, based on the information used. It is evaluated according to the Guide to the Expression of Uncertainty in Measurement (GUM).
- Sensors
- Standards
In one sentence
Measurement uncertainty quantifies the range of values reasonably attributed to a measurand; it is evaluated according to the GUM.
Example
A calibration certificate states 100.02 °C with an expanded uncertainty of 0.05 °C (k = 2), meaning a coverage probability of about 95 %.
How it applies
- Engineering: An uncertainty budget combines contributions such as the reference standard, resolution, repeatability, temperature effects and drift. Type A contributions come from statistical analysis, type B from other information such as datasheets.
- Quality and safety: When a value is compared with a limit, the uncertainty decides whether conformity can be stated. A reading just below a limit may not prove conformity if the uncertainty is larger than the margin; decision rules define how this is handled.
- Calibration: Accredited laboratories under ISO/IEC 17025 state the uncertainty of their results as part of Measurement traceability.
- Documentation: Report uncertainty with its coverage factor. Avoid mixing up uncertainty with tolerance or accuracy class in manuals and test reports.
Measurement uncertainty vs. measurement error
The error is the difference between a measured value and a reference value; known systematic errors can be corrected. Uncertainty describes the remaining doubt about the result after corrections.