There are exactly two types of variation that a control chart is designed to monitor.
Control charts are fundamental tools in statistical process control (SPC) used to monitor, analyze, and improve process performance over time. Their primary purpose is to help distinguish between two distinct types of variation that can occur in any process, enabling appropriate management action.
The Two Types of Variation in Control Charts
According to a reference from Minitab, a leading statistical software, control charts are specifically designed to monitor two types of process variation: common-cause variation and special-cause variation.
Let's explore each type in detail:
1. Common-Cause Variation (Random Variation)
Common-cause variation, also known as random variation or inherent variation, represents the natural and expected variability within a stable process. It is due to the cumulative effect of many small, unpredictable, and unavoidable factors that are always present in the system.
- Characteristics:
- Inherent to the process design and operation.
- Predictable within a certain range.
- Represents a process that is "in statistical control" or "stable."
- Small, chronic, and consistent over time.
- Examples:
- Slight fluctuations in ambient temperature.
- Minor differences in raw material consistency within specifications.
- Normal wear and tear of machinery.
- Minute variations in operator technique.
- Action Required: Addressing common-cause variation typically requires fundamental changes to the process itself, such as redesigning the system, investing in new equipment, or implementing new training programs. This is a management responsibility, not usually an operator's.
2. Special-Cause Variation (Assignable Cause Variation)
Special-cause variation, also known as assignable cause variation, refers to variations that arise from specific, identifiable, and often external factors not inherent in the process. These causes lead to unexpected shifts or patterns in the process output, indicating that the process is "out of statistical control" or "unstable."
- Characteristics:
- Not inherent to the process; comes from external or new factors.
- Unpredictable in terms of timing and magnitude.
- Indicates a process that is "out of statistical control."
- Often large, intermittent, and specific.
- Examples:
- A sudden change in a raw material supplier.
- Machine malfunction or breakdown.
- An untrained operator performing a critical task.
- A power surge or equipment calibration error.
- A significant shift in environmental conditions (e.g., unexpected humidity).
- Action Required: Special causes should be investigated immediately, identified, and eliminated to bring the process back into a state of statistical control. This often involves specific, local actions by operators or supervisors.
Differentiating Variation with Control Charts
Control charts provide visual boundaries, known as control limits (upper control limit - UCL and lower control limit - LCL), that are statistically determined from the process data itself.
- Within Control Limits: Data points falling randomly within the control limits, with no discernible patterns, indicate that only common-cause variation is present, and the process is stable.
- Outside Control Limits or Non-Random Patterns: Data points falling outside the control limits, or exhibiting non-random patterns (like runs above or below the center line, trends, or cycles), signal the presence of special-cause variation.
Summary of Variation Types
| Feature | Common-Cause Variation | Special-Cause Variation |
|---|---|---|
| Nature | Inherent, random | External, assignable |
| Predictability | Predictable within a range | Unpredictable |
| Process State | In statistical control (stable) | Out of statistical control (unstable) |
| Impact | Chronic, small, constant | Intermittent, potentially large |
| Root Cause | Systemic (part of the process) | Specific (external event or factor) |
| Action Required | Change the system (management) | Find and eliminate the cause (local) |
| Control Chart Ind. | Points within control limits | Points outside limits, patterns |
Importance of Understanding Variation
Understanding the difference between common-cause and special-cause variation is crucial for effective process management:
- Prevents Misinterpretation: It stops managers from overreacting to common-cause variation (tampering with a stable process) or underreacting to special-cause variation (missing a critical issue).
- Directs Correct Action: Knowing the type of variation dictates the appropriate response, ensuring that improvement efforts are targeted correctly and effectively.
- Facilitates Continuous Improvement: By systematically eliminating special causes and then working to reduce common causes, organizations can continuously improve the stability and capability of their processes.
