Accuracy and precision in measurement systems

Accuracy and precision are two characteristics of an acceptable gage.
Accuracy
Accuracy refers to how close a gage's measurements are to the true value. To assess accuracy, use a gage linearity and bias study (Stat > Quality Tools > Gage Study > Gage Linearity and Bias Study) or a type 1 gage study (Stat > Quality Tools > Gage Study > Type 1 Gage Study).
Precision
Precision refers to how close measurements are to each other. To assess precision, use a crossed, nested, or expanded gage R&R study (Stat > Quality Tools > Gage Study).

A gage can have any combination of accuracy and precision. For example, a gage that measures medication tablets is precise but not accurate if it measures the same 200 mg tablet as 205.54 mg, 205.43 mg, and 205.03 mg. The gage's measurements are close to each other, and thus precise. But they are not close to the true value (200 mg), and thus not accurate.

Accurate and precise
Accurate and precise

Measurements are close to the true value and are close to each other.

Accurate and precise
Precise but not accurate

Measurements are close to each other but not close to the true value.

Accurate and precise
Accurate but not precise

Measurements are close to the true value but not close to each other.

Accurate and precise
Not accurate or precise

Measurements are not close to the true value or close to each other.

The accuracy of a measurement system has three components: bias, linearity, and stability. The precision of a measurement system has two components: repeatability and reproducibility. These components can be studied in more detail with various gage studies.

Note

The integrity of your data depends on the integrity of your measurement system. If you detect problems with accuracy and precision, you must improve the measurement system before you can trust your data.

By using this site you agree to the use of cookies for analytics and personalized content.  Read our policy