Abstract

Physicist Walter Shewhart, in tackling the problem of process control, began with the definition of control and went on to distinguish chance causes from assignable causes of variation. He believed that assignable causes could be found and eliminated. The first published control chart was an internal Bell Telephone Laboratories report in 1924. Shewhart, also an empiricist, based his control chart limits on the economics of change rather than on underlying probabilities. His run charts were drawn with limits based on marked improvements from previous periods of inspection. Statistical process control, which originally referred only to the application of control charts, now refers to the application of statistical tools to the improvement of quality and productivity, with control charts as one of the preeminent tools.