Precision
Definition
The degree to which repeated measurements of the same specimen under the same conditions agree with each other. Quantified by the standard deviation or coefficient of variation of replicate measurements. A precise method has low scatter regardless of whether it is centred on the true value.
- Definition
- Agreement among repeated measurements of the same specimen
- Quantified by
- Standard deviation or coefficient of variation
- Independent of
- Whether results are centred on the true value
- Contrast
- Accuracy, which measures closeness to the true value
Common questions
Can a measurement method be precise but inaccurate?+
Yes. A method with low scatter can still be systematically offset from the true value due to calibration error or bias, producing results that cluster tightly together but consistently miss the correct answer, which is why precision and accuracy are reported and validated separately.
Why does a forensic lab need to document both precision and accuracy for a method?+
Validation records that establish both the scatter of repeated results and their closeness to a known reference value give the lab, and later a court, a defensible basis for stating the uncertainty attached to any single reported measurement.
Related terms
- Accuracy
- The degree to which a measured value agrees with the accepted true or reference value of the quantity. A biased instrument can...
- Between-Class Variability
- The spread of measurements between items from different sources or categories. A forensic method is most discriminating when between-class variability is large...
- Bias
- Bias is a systematic tendency for an estimate or measurement to depart from its target under specified conditions. It differs from random...
- Expanded Uncertainty
- The combined standard uncertainty multiplied by a coverage factor k, chosen to achieve a stated coverage probability. For a normal distribution, k...
- Measurement Error
- The discrepancy between a recorded value and the true value of the property being measured. Arises from instrument calibration limits, analyst technique,...
- Proficiency Testing
- Assessment of participant performance against defined criteria; an exercise is not necessarily blind. It may test identification, calculation, interpretation or a broader...
- Repeatability
- The agreement between successive measurements of the same specimen made by the same analyst, on the same instrument, in the same laboratory,...
- Standard Uncertainty
- Measurement uncertainty expressed as a standard deviation.
- Validation
- Documented evaluation that a method is fit for a stated purpose under specified conditions. Laboratory development data and realistic field performance provide...
- Verification
- Verification provides objective evidence that specified requirements have been met for a method, system or result under a defined application. In laboratory...
- Within-Class Variability
- The natural spread of measurements among items that share a common source, class, or category. For example, the range of refractive index...
Explained in these topics
- Method Validation, Measurement Uncertainty and Proficiency TestingAgreement among repeated results under stated conditions.
- Variability and Measurement Error