Mathematics of Control Charts
Digital control charts use logic based rules that determine "derived values" which signal the need for correction. For example,
- derived value = last value + average absolute difference between the last N numbers.
Most SPC charts work best using numeric data with Gaussian assumptions. Recently a new type of control chart, the real-time contrasts chart was developed in order to handle process data with complex characteristics. Such data might include high-dimensional data; mixed numerical and categorical data; data with missing values; and data with non-Gaussian distributions or with non-linear relationships.
Read more about this topic: Statistical Process Control
Famous quotes containing the words mathematics, control and/or charts:
“It is a monstrous thing to force a child to learn Latin or Greek or mathematics on the ground that they are an indispensable gymnastic for the mental powers. It would be monstrous even if it were true.”
—George Bernard Shaw (1856–1950)
“For the mother who has opted to stay home, the question remains: Having perfected her role as a caretaker, can she abdicate control to less practiced individuals? Having put all her identity eggs in one basket, can she hand over the basket freely? Having put aside her own ambitions, can she resist imposing them on her children? And having set one example, can she teach another?”
—Melinda M. Marshall (20th century)
“There’s one basic rule you should remember about development charts that will save you countless hours of worry.... The fact that a child passes through a particular developmental stage is always more important than the age of that child when he or she does it. In the long run, it really doesn’t matter whether you learn to walk at ten months or fifteen months—as long as you learn how to walk.”
—Lawrence Kutner (20th century)