Tolerance interval
From Wikipedia, the free encyclopedia
A tolerance interval is a statistical interval within which, with some confidence, a specified proportion of a population falls. This differs from a confidence interval in that the confidence interval bounds a population parameter (the mean or variance, for example) with some confidence, while the bounds of a tolerance interval are a range of possible data values that represents a specified proportion of the population. In simpler terms, a confidence interval characterizes what is known about a single quantity while a tolerance interval characterizes what is known about values across a collection of items.
If the confidence is 100%, because the population distribution parameters are known exactly, then the tolerance interval reduces to a probability interval.
[edit] External links
- See The NIST/SEMATECH e-Handbook of Statistical Methods, 2004 July 17.
- In particular Section 7.2.6.3 - Tolerance intervals for a normal distribution
- See "Quality Control Handbook", Juran.