Keep test variables in line

An inaccurate ATE system will yield poor test results, which in turn can reduce profits by causing you to fail good parts or pass bad parts. Using a statistical method, you can predict the accuracy of your ATE system and the measurements it makes.

Gresham bases his statistics on the Central Limit Theorem: "The distribution of an average tends to be Normal, even when the distribution from which the average is computed is decidedly non-Normal" (Ref. 1).To achieve a normal distribution, Gresham always takes at least 30 measurements of each electrical parameter, from which he calculates the mean and standard deviation.

Gresham provides more details about his method in "The Economics of Using SPC in a Manufacturing Test Environment," a paper that you can download.