In the 1920's, Dr. Walter Shewhart, a statistician, was working in the laboratories of Bell Telephone Company in the USA. He had done a great deal of work on the concept of variability in the natural world, and was asked by Bell to apply the same techniques to finding out why there was so much variability between the telephones they produced.
Dr. Shewhart's research led him to the conclusion that:
While every process displays variation, some processes display controlled variation while others display uncontrolled variation.
Controlled variation shows a stable and consistent pattern over time, and is therefore always present in the process. Dr. Shewhart attributed such variation to chance causes affcting the process.
On the other hand, uncontrolled variation shows a pattern that changes over time, and which therefore means that the process itself is both inconsistent and unstable.