Statistical quality control: Overview
What it does
The job the technology does for people, in a short paragraph
Statistical quality control tells a process that is drifting from one that is only showing its normal scatter. Workers sample parts as they are made and plot the results on a control chart, so they fix real faults and leave a stable process alone. Walter Shewhart proposed the chart in 1924 [1], and by 1937 a dozen or more mass-production industries used the methods routinely [2].
as of 2026-11-11
How it works
The working principle in plain words, step by step
Every process varies a little, even when nothing is wrong. Shewhart's idea was to measure how big that normal scatter is and to treat only larger swings as a sign of trouble. At set times a few parts are measured and their average, or range, is plotted on a chart [2]. A centre line marks the usual value. Control limits are drawn above and below it, usually at three standard deviations, a measure of the normal scatter [3]. If the process is stable, a point falls outside these 3-sigma limits only about 0.27% of the time [3]. So a point beyond them, or a run of points drifting one way, is worth a search for a cause such as a worn tool or a new batch of material.
as of 2026-11-11
Key figures
The handful of numbers that size it up, each with its unit, year and source
| Figure | Value | Unit | Year | Source |
|---|---|---|---|---|
| Usual width of control limits | 3 | standard deviations either side of the centre line | – | [3] |
| Chance that a stable, normally distributed process falls outside 3-sigma limits | 0.003 | probability | – | [3] |
| Mass-production industries using the methods in normal operation | 12 | industries (a dozen or more) | 1937 | [2] |
| Local quality control societies that formed the American Society for Quality Control | 17 | societies | 1946 | [2] |
as of 2026-11-11. The 3-sigma figures are standard statistics; the NIST handbook page shows no year of any kind, so they carry none [3]. The 1937 and 1946 rows are the years the events happened [2].
Where it is used
The main places and products the technology is found in
- Inspection of parts on factory production lines
- Monitoring chemical and process plants
- Telephone and electronics manufacturing, where the method began
- Wartime factory production under the American war standards for control charts [2]
- Hospitals and health care improvement teams [6]
- Quality software that charts data from machines and laboratories
as of 2026-11-11
Sources
- Walter A. Shewhart: Father of statistical quality control American Society for Quality (ASQ), honorary members pages
- Chapter 1 Introduction Historical Background | An Introduction to Acceptance Sampling and SPC with R John Lawson, bookdown.org
- 6.3.1. What are Control Charts? NIST/SEMATECH e-Handbook of Statistical Methods, US National Institute of Standards and Technology
- 100th Anniversary of the Shewhart Chart: Why Do We Care? Rebecca Steinfield and Robert Lloyd, Institute for Healthcare Improvement (IHI), 2024