Brooks/Cole, Canada, 2007, 967 - 988, unless otherwise attributed.
"Every physical measurement is subject to a degree of uncertainty that, at best, can only be decreased to an
acceptable level. The determination of the magnitude of this uncertainty is often difficult and requires
additional effort, ingenuity, and good judgment on the part of the observer. Nevertheless, evaluation of the
uncertainty in analytical data is a task that cannot be neglected because a measurement of totally unknown
reliability is worthless." (
, Saunders College
Publishing, PA, 1982, 25.)
Precision and Accuracy
Two terms are widely used in discussions of the reliability of data: precision and accuracy.
describes the reproducibility of results, that is, the agreement between numerical values for two
or more replicate measurements, or measurements that have been made in
exactly the same way.
the precision of an analytical method is readily obtained by simply repeating the measurement.
Three terms are widely used to describe the precision of a set of replicate data: standard deviation, variance,
and coefficient of variation. These terms have statistical significance.
describes the correctness of an experimental result expressed as the closeness of the measurement
to the true or accepted value. Accuracy is expressed in terms of either absolute error or relative error. The
absolute error E
of the mean (or average)
of a small set of replicate analyses is given by the relationship
is the true or accepted value of the quantity being measured. Often, it is useful to express the
accuracy in terms of the
We will be concerned with two types of errors,
We will give random error the symbol
error the symbol
The error in the mean of a set of replicate measurements is then the sum of these two
types of errors:
Systematic or Determinant Errors
have a definite value and an assignable cause and are of the same magnitude for replicate
measurements made in the same way. Systematic errors lead to
in measurement results. Bias is
illustrated by the two curves in Figure 2, which show the frequency distribution of replicate results in the
analysis of identical samples by two methods that have random errors of identical size. Method
bias so that the mean
is the true value. Method
has a bias that is given by