What Is Statistical Process Control?
Statistical process control uses statistical methods to monitor and control a process over time, distinguishing between common cause variation, which is the normal, expected fluctuation inherent to any process, and special cause variation, which signals that something unusual has affected the process and warrants investigation. RHIA candidates should understand control charts as a core tool for this monitoring.
Anatomy of a Control Chart
A control chart plots data points over time against a center line representing the process average, along with upper and lower control limits typically set at three standard deviations from the mean. As long as data points fall randomly within the control limits, the process is considered to be in statistical control, meaning only common cause variation is present.
Signals of Special Cause Variation
- A single data point falling outside the upper or lower control limit
- A run of several consecutive points on the same side of the center line
- A clear trend of points steadily increasing or decreasing over several periods
- Unusual patterns such as cycling or points clustering too tightly around the center line
Types of Control Charts
An X-bar and R chart is used for continuous data collected in subgroups, such as average length of stay measured weekly. A p-chart monitors the proportion of defective items in a sample, useful for tracking metrics like the percentage of delinquent health records or claim denial rates, since these are expressed as proportions of a total.
Application in HIM Quality Monitoring
HIM departments can apply control charts to monitor coding accuracy rates, release of information turnaround times, and discharged-not-final-billed trends, helping leaders determine when a shift in performance reflects a true process problem requiring intervention versus normal day-to-day variability that does not warrant a knee-jerk reaction.
Avoiding Overreaction to Common Cause Variation
A key principle of statistical process control is that reacting to every fluctuation within control limits, known as tampering, can actually increase variation and destabilize an otherwise well-functioning process. Leaders should intervene only when data signals special cause variation.
Exam Tip
Remember that the goal of a control chart is to differentiate common cause from special cause variation, and that intervention should be reserved for signals of special cause variation only.