## What Is a Control Chart

Run charts and control charts are similar in that they both use time-ordered data. The difference is that control charts provide limits within which observed variation can be characterized as random and expected, and outside which you can recognize variation as extraordinary. With control charts you have more ways than run charts provide to detect special cause signals.

As mentioned earlier there are three common rules for detecting special cause signals in run charts. These same rules apply to control charts but additional rules can be used with control charts because they have an added feature, calculated upper and lower control limits, or upper and lower natural process limits, that can be used to detect special causes in your process.

We illustrate the essential difference between these two types of trend charts in Figures 22.6 and 22.7.

Figure 22.6 shows the gross anatomy of a run chart. It has a variable, X, whose value is measured on the vertical dimension and is shown at each point in a time-ordered sequence on the horizontal dimension. The run chart also has a center line based on either the calculated average value or the median value of the points.

Figure 22.7 shows the gross anatomy of a control chart. It has all the features of the run chart but in addition has upper and lower calculated limits. These calculated limits are shown, by convention, as dotted lines and are called the upper control limit (UCL) and lower control limit (LCL), respectively. Another set of terms for these calculated limits, one that Wheeler prefers (1993, 1995), is upper natural process limit and lower

FIGURE 22.6. GROSS ANATOMY OF A RUN CHART.

> Center line

Time-Ordered Observations (1-n)

FIGURE 22.7. GROSS ANATOMY OF A CONTROL CHART.

FIGURE 22.8. CONTROL CHART FOR INDIVIDUALS WITH DIABETES IN A GENERAL MEDICINE PRACTICE.

FIGURE 22.8. CONTROL CHART FOR INDIVIDUALS WITH DIABETES IN A GENERAL MEDICINE PRACTICE.

Patient

natural process limit. Wheeler prefers this terminology because it is a better reflection of the principle of special cause and common cause variation, described earlier.

In general you can interpret the results of a run chart by looking for data points above the upper limit or below the lower limit. If a data point falls outside these calculated upper or lower limits, it is a special cause signal, because the likelihood that a point will fall outside these limits due to a common cause is very low (less than 1 out of 100).

Figure 22.8 provides a real-life example of a control chart, one that a physician colleague of ours (Mark Splaine) used to measure progress in managing blood sugar levels in his patients with diabetes. This figure shows that after Splaine made changes in his practice, the average level of blood sugar control improved and the variation over time was reduced.

Was this article helpful?

0 0

## Positive Thinking As The Key To Success

Download this Guide and Discover How To Find And Monetize on Your Expertise And Strengths. Inside this special report, you'll discover: How positive thinking is one of the key factors in a successful life. Five ways and tools to help you stay positive. Use these to help you keep on track. Case studies that'll inspire you to stick to your dreams. Plus much, much more.

Get My Free Ebook