Useful Terms

Question 1

Accuracy

Answer 1

Accuracy is a measure of the closeness of agreement between an individual test result and the true value. If a test result is accurate, it is in close agreement with the true value. An accepted reference value may be used as the true value, though in practise the true value is usually not known.

Question 2

Anomaly (outlier)

Answer 2

An anomaly is a value in a set of results that is judged not to be part of the inherent variation.

Question 3

Confidence

Answer 3

Confidence is a qualitative judgement expressing the extent to which a conclusion is justified by quality of the evidence.

Question 4

Error (of measurement)

Answer 4

Error of measurement is the difference between an individual measurement and the true value (or accepted reference value) of the quantity being measured.

Question 5

Precision

Answer 5

Precision is the closeness of agreement between independent measurements obtained under the same conditions. It depends only on the distribution of random errors (i.e. the spread of measurements) and does not relate to the true value.

Question 6

Repeatability

Answer 6

Repeatability is the precision obtained when measurement results are produced over a short timescale by one person (or the same group) using the same equipment in the same place.

Question 7

Reproducibility

Answer 7

Reproducibility is the precision obtained when measurement results are produced over a wider timescale by different people using equivalent equipment in different (but equivalent) places.

Question 8

Resolution

Answer 8

Resolution is the smallest change in the quantity being measured that can be detected by an instrument.

Question 9

Uncertainty

Answer 9

Uncertainty is an estimate attached to a measurement which characterises the range of values within which the true value is asserted to lie. This is normally expressed as a range of values such as 44.0 +- 0.4

Question 10

Validity

Answer 10

Validity can apply to an individual measurement or a whole investigation. A measurement is valid if it measures what it is supposed to be meaning. An investigative procedure is valid if it is suitable to answer the question being asked. Validity will be reduced, for example, if no negative control is included in an investigation into the efficacy of a therapeutic drug.