Pursuant to our objective to provide the highest quality certificate to the industry with objective and testable level of performance, we define a number of concepts essential for the purpose of understanding and evaluating the contents of a Certificate. Objective assessment of performance requires clear understanding of three concepts; accuracy, precision and repeatability.
Accuracy is defined in terms of the difference between a measurement of
a standard and an average of measurements obtained by a system. If the
average of measurements equals the true value, statisticians say a system is
unbiased or accurate.
(Farnum, Nicholas R. 1994. Modern Statistical Quality Control and
Improvement, Duxbury).
Precision is defined as the number of decimal places used for measurements. For example: an instrument which reads a linear measurement to three decimal places is more precise than one which reads to two or one decimal place, quid pro quo. It is desirable to have higher precision as the value of a gemstone increases.
Repeatability represents variation between repeated measurements.
Repeatability, also called consistency is measured by the standard deviation
of the measurements. Repeatability may be stated, for example, as
within plus or minus 10 microns with say 95% probability. The smaller
the range of repeatability for a given level of probability, the higher is
the reliability of a system.
(Farnum, Nicholas R. 1994. Modern Statistical Quality Control and
Improvement, Duxbury).
Inaccurate and not repeatable Accurate, but not repeatable Inaccurate but repeatable Accurate and repeatable
(a) (b) (c) (d)
(Farnum, Nicholas R. 1994. Modern Statistical Quality Control and Improvement, Duxbury).