Common cause variation

Common cause variation refers to the inherent, natural fluctuation present in any process over time, affecting every outcome and everyone working within that process. This type of variation was originally termed "chance cause" by Walter A. Shewhart in his pioneering work at Bell Telephone Laboratories during the 1920s^[1]. The concept forms a cornerstone of statistical process control and quality management.

Historical development

On May 16, 1924, Walter A. Shewhart prepared a memorandum for his supervisor George D. Edwards at Western Electric's Hawthorne Works. About one-third of that single page contained a diagram that would become known as the control chart^[2]. This document marked the birth of statistical quality control.

Shewhart distinguished between two types of variation: chance-cause variation (inherent and random) and assignable-cause variation (intermittent and identifiable). Harry Alpert coined the term "common cause" in 1947. W. Edwards Deming later adopted and popularized this terminology, introducing the companion term "special cause" for assignable variation.

Shewhart's work was summarized in his 1931 book Economic Control of Quality of Manufactured Product. The American Society for Testing and Materials (ASTM) adopted Shewhart's charts in 1933. During World War II, these methods were incorporated into American War Standards Z1.1-1941, Z1.2-1941, and Z1.3-1942 to improve wartime production.

Characteristics of common cause variation

Common cause variation displays several defining features:

Present in every process outcome
Stable and predictable over time (at least approximately in frequency)
Inherent to the process design and execution
Results from the combined effect of many small, often unmeasurable factors
Cannot be reduced without changing the process itself

A process exhibiting only common cause variation is said to be "in statistical control" or "stable." Such processes behave predictably within established control limits.

Distinguishing common from special cause variation

Control charts provide the primary tool for distinguishing between variation types. Data points falling outside the upper control limit (UCL) or lower control limit (LCL) generally indicate special causes. Patterns such as continuous increases or decreases, runs above or below the center line, or cyclical behavior also suggest special causes at work.

When data appear random and remain within control limits, the variation is typically common cause variation. This distinction matters greatly for management decision-making.

Management implications

Deming estimated that failing to understand variation led to situations where 95% of management actions produced no improvement^[3]. He identified two fundamental mistakes:

Treating a common cause as if it were a special cause (tampering)
Treating a special cause as if it were a common cause (neglecting assignable problems)

Tampering occurs when managers react to normal variation by adjusting a stable process. Each adjustment adds variation rather than reducing it. This phenomenon was demonstrated by Deming's famous "funnel experiment."

Addressing common cause variation requires systemic changes to the process. Management bears responsibility for creating and improving systems. Workers typically cannot reduce common cause variation without management-initiated process redesign, training, or resource allocation.

Relationship to continuous improvement

Reducing common cause variation demands process improvement initiatives. Organizations may employ methods such as:

Process redesign or reengineering
Investment in better equipment or materials
Enhanced training programs
Revised procedures and standardized work

The goal is reducing the natural spread of the process while maintaining it in a state of statistical control.

{{{Concept}}} Primary topic {{{list1}}} Related topics {{{list2}}} Methods and techniques {{{list3}}}

References

Shewhart, W.A. (1931). Economic Control of Quality of Manufactured Product. Van Nostrand.
Deming, W.E. (1986). Out of the Crisis. MIT Press.
Wheeler, D.J. and Chambers, D.S. (1992). Understanding Statistical Process Control. SPC Press.

Footnotes

Shewhart, W.A. (1931). Economic Control of Quality of Manufactured Product. Van Nostrand.
Edwards, G.D. recalled in various accounts of the May 16, 1924 memorandum at Bell Telephone Laboratories.
Deming, W.E. (1986). Out of the Crisis. MIT Press.

Author

Sławomir Wawak