Accuracy and Precision
Accuracy (Trueness) and Inaccuracy (Bias)
Accuracy describes the "closeness of agreement" between a measured value and a true or accepted reference value. In modern metrology (ISO 5725), the specific term for the closeness of the mean of a set of results to the true value is Trueness.
Systematic Error (Inaccuracy) is a consistent deviation in measurements in a single direction. It is quantified as Bias—the average numerical difference between your test method and the reference value.
Precision and Imprecision (Random Error)
Precision refers to the consistency or "closeness of agreement" between independent measurements obtained under stipulated conditions. Precision is concerned only with how well results cluster together, regardless of where they hit relative to the "True Value."
Imprecision (Random Error) refers to unpredictable, inherent fluctuations in measurements. It is usually quantified by the Standard Deviation (SD) or the Coefficient of Variation (CV%).
Categories of Precision are:
- Repeatability: Consistency when measurements are taken by the same operator, on the same equipment, within a short period (within-run).
- Reproducibility: Consistency when measurements are taken across different days, different operators, or different laboratories (between-run).
Total Analytic Error (TAE)
In clinical laboratory science, we rarely look at accuracy or precision in isolation. We evaluate the Total Error. A result is only clinically useful if the combination of its bias (systematic error) and its imprecision (random error) stays within acceptable limits for patient care.
A common simplified formula for estimating the maximum error is:
where
- Bias is the difference between the average measured value and the target value.
- SD is the standard deviation of replicate measurements.
Graphical representation
Literature
- Westgard JO (2008) Basic method validation. 3rd ed. Madison: Westgard QC, Inc.