Statistical Quality Control: Meaning and Causes of Variation

Statistical Quality Control (SQC) is the use of statistical methods to monitor and control the quality of a manufacturing process while production is actually going on, rather than only inspecting finished goods afterward. No manufacturing process, however carefully run, produces items that are perfectly identical — some small variation between one unit and the next is always present. SQC's central idea is to distinguish between two very different kinds of variation:

Chance (random) causes are the many small, unavoidable influences — minor differences in raw material, slight vibration of a machine, small temperature changes, the operator's natural hand movement — each too small to identify or eliminate individually, and together producing a stable, predictable pattern of natural variation. A process affected only by chance causes is said to be in (statistical) control.

Assignable causes are large, identifiable, and preventable sources of variation — a worn-out tool, an untrained operator, a defective batch of raw material, a machine that has slipped out of adjustment. Unlike chance causes, assignable causes can and should be traced to their source and removed. A process affected by an assignable cause is said to have gone out of control.