Control charts serve as one of the most powerful tools in quality management and process improvement. Whether you’re managing a manufacturing line, overseeing a service department, or monitoring any process that generates measurable data, understanding how to create and interpret control charts can transform your ability to maintain consistency and identify problems before they escalate.
This comprehensive guide will walk you through everything you need to know about control charts, from basic concepts to practical implementation, complete with real-world examples and sample data to help you get started. You might also enjoy reading about How to Perform the Shapiro-Wilk Test: A Complete Guide to Testing Data Normality.
What is a Control Chart?
A control chart, also known as a Shewhart chart or process behavior chart, is a statistical tool used to monitor whether a process remains in a state of statistical control over time. Developed by Walter A. Shewhart in the 1920s while working at Bell Laboratories, this tool plots data points in time order and includes a central line representing the average, along with upper and lower control limits that define the boundaries of normal process variation. You might also enjoy reading about How to Create and Use an I Chart for Process Monitoring: A Complete Guide.
The primary purpose of a control chart is to distinguish between two types of variation: common cause variation (the natural, expected variation inherent in any process) and special cause variation (unusual variation that signals something has changed in the process). This distinction is critical because it helps you make informed decisions about when to intervene in a process and when to leave it alone.
Understanding the Components of a Control Chart
Before you can create an effective control chart, you need to understand its essential components:
- Center Line (CL): Represents the average or mean of the process data
- Upper Control Limit (UCL): The upper boundary, typically set at three standard deviations above the center line
- Lower Control Limit (LCL): The lower boundary, typically set at three standard deviations below the center line
- Data Points: Individual measurements plotted in chronological order
- Time Axis: The horizontal axis showing the sequence of measurements
- Measurement Axis: The vertical axis showing the value of the characteristic being measured
Types of Control Charts
Different types of control charts suit different types of data. The two main categories are variable control charts (for continuous data) and attribute control charts (for discrete data).
Variable Control Charts
These charts are used when you can measure your quality characteristic on a continuous scale. The most common types include:
- X-bar and R Chart: Used for monitoring the mean and range of a process when you have subgroups of data
- X-bar and S Chart: Similar to X-bar and R, but uses standard deviation instead of range
- Individual and Moving Range (I-MR) Chart: Used when you can only collect one measurement at a time
Attribute Control Charts
These charts work with count data or data that can be categorized into two groups (pass/fail, yes/no). Common types include:
- P Chart: Tracks the proportion of defective items
- NP Chart: Monitors the number of defective items
- C Chart: Counts defects per unit when sample size is constant
- U Chart: Tracks defects per unit when sample size varies
Step-by-Step Guide: Creating Your First Control Chart
Let’s walk through creating an Individual and Moving Range (I-MR) control chart using a practical example. Imagine you manage a call center and want to monitor the average call handling time in minutes.
Step 1: Collect Your Data
Gather at least 20 to 25 data points for reliable control limits. Here’s our sample dataset showing daily average call handling times over 25 days:
Day 1: 8.2, Day 2: 7.9, Day 3: 8.5, Day 4: 8.1, Day 5: 7.8, Day 6: 8.3, Day 7: 8.0, Day 8: 7.7, Day 9: 8.4, Day 10: 8.2, Day 11: 7.9, Day 12: 8.1, Day 13: 8.3, Day 14: 8.0, Day 15: 7.8, Day 16: 8.2, Day 17: 8.5, Day 18: 7.9, Day 19: 8.1, Day 20: 8.0, Day 21: 8.3, Day 22: 7.7, Day 23: 8.4, Day 24: 8.1, Day 25: 8.2
Step 2: Calculate the Center Line
Add all your data points and divide by the number of observations. For our call center example:
Center Line = Sum of all values / Number of values = 202.6 / 25 = 8.1 minutes
Step 3: Calculate the Moving Range
The moving range is the absolute difference between consecutive data points. For example, the moving range between Day 1 and Day 2 is |8.2 – 7.9| = 0.3. Calculate this for all consecutive pairs.
Our moving ranges are: 0.3, 0.6, 0.4, 0.3, 0.5, 0.3, 0.3, 0.7, 0.2, 0.3, 0.2, 0.2, 0.3, 0.2, 0.4, 0.3, 0.6, 0.2, 0.1, 0.3, 0.6, 0.7, 0.3, 0.1
Step 4: Calculate Average Moving Range
Average Moving Range = Sum of moving ranges / Number of moving ranges = 8.4 / 24 = 0.35
Step 5: Calculate Control Limits
For an Individual chart, use these formulas:
UCL = Center Line + (2.66 × Average Moving Range) = 8.1 + (2.66 × 0.35) = 9.03 minutes
LCL = Center Line – (2.66 × Average Moving Range) = 8.1 – (2.66 × 0.35) = 7.17 minutes
Step 6: Plot Your Chart
Create a graph with time on the horizontal axis and call handling time on the vertical axis. Draw horizontal lines for your center line (8.1), UCL (9.03), and LCL (7.17). Plot each day’s average call time as a point and connect them with lines.
Interpreting Your Control Chart
Once you’ve created your control chart, knowing how to read it properly is essential. A process is considered out of control if you observe any of these patterns:
Rule 1: Points Beyond Control Limits
If any point falls outside the upper or lower control limits, this indicates special cause variation. In our call center example, if Day 26 showed an average call time of 9.5 minutes, this would exceed the UCL and warrant investigation.
Rule 2: Runs and Trends
Watch for seven or more consecutive points all above or all below the center line, or seven or more points consistently increasing or decreasing. These patterns suggest the process has shifted.
Rule 3: Cycles or Patterns
Regular cycles in your data might indicate special causes related to time periods, such as different shifts, days of the week, or seasonal factors.
Rule 4: Points Near Control Limits
Two out of three consecutive points falling in the outer third of the chart (between the center line and control limit) may signal increased variation.
Taking Action Based on Control Chart Results
When your control chart indicates a process is in control with only common cause variation, resist the temptation to make adjustments. Tampering with a stable process typically increases variation rather than reducing it. Focus instead on systemic improvements to the entire process.
When you detect special cause variation, investigate immediately to identify the root cause. Was there new staff on that day? Equipment malfunction? Changes in procedures? Document your findings and implement corrective actions to prevent recurrence.
Common Mistakes to Avoid
Many organizations struggle with control charts due to these common errors:
- Using specification limits instead of control limits
- Calculating control limits from non-homogeneous data
- Failing to update control limits when process improvements are made
- Reacting to every variation rather than distinguishing between common and special causes
- Not collecting enough data points before establishing control limits
Benefits of Implementing Control Charts
Organizations that effectively use control charts experience numerous benefits. They gain objective evidence about process performance, enabling data-driven decisions rather than relying on gut feelings. Control charts provide early warning signals about process problems, allowing teams to intervene before defects reach customers. They also reduce waste by preventing unnecessary process adjustments and help teams focus improvement efforts where they will have the greatest impact.
Furthermore, control charts create a common language for discussing process performance across departments and shifts, facilitating better communication and collaboration throughout the organization.
Advancing Your Skills in Process Improvement
Control charts represent just one component of a comprehensive quality management toolkit. To truly master process improvement and bring transformative results to your organization, consider deepening your expertise through formal training in methodologies like Lean Six Sigma.
Lean Six Sigma combines the waste-reduction principles of Lean manufacturing with the variation-reduction techniques of Six Sigma, providing you with a powerful framework for driving operational excellence. Through structured training, you’ll learn not only control charts but also value stream mapping, root cause analysis, design of experiments, process capability analysis, and many other essential tools.
Professional certification demonstrates your commitment to quality and significantly enhances your career prospects. Organizations worldwide actively seek professionals with Lean Six Sigma credentials to lead improvement initiatives and drive bottom-line results.
Take the Next Step in Your Quality Journey
Understanding control charts opens the door to more effective process management, but mastering the complete toolkit of quality improvement methods will multiply your impact exponentially. Whether you’re just beginning your quality journey or looking to formalize existing knowledge, investing in comprehensive training pays dividends throughout your career.
Enrol in Lean Six Sigma Training Today and gain the skills, confidence, and credentials to lead meaningful change in your organization. Join thousands of professionals who have transformed their careers and their companies through structured quality improvement methodologies. Your journey toward operational excellence starts with a single step. Take that step today.
