R-диаграмма

An R chart, or range chart, measures the variability within process subgroups rather than individual values. It tracks the spread of measurements in samples, such as weight ranges of bread loaves in a bakery. The chart helps detect shifts in process variability by plotting sample ranges against a centerline representing the average range and statistical control limits.

Control limits on an R chart define the expected boundaries of process variability. When all plotted data points remain within the upper and lower control limits without predictable patterns, the process is considered stable. Data points exceeding these limits signal potential process anomalies, such as equipment issues, requiring immediate investigation and corrective action.

R charts offer deeper insights into non-random process variations than run charts, which only display data trends over time. While run charts show overall patterns, R charts specifically assess variability within subgroups, enabling detection of subtle shifts in process consistency. This makes R charts indispensable for proactively identifying anomalies in manufacturing and healthcare applications.

An R chart comprises three key components: the centerline, which represents the average range of all samples; the upper control limit, derived from statistical norms; and the lower control limit. Together, these elements map the expected process variability and establish boundaries for determining whether observed ranges reflect normal variation or signal process problems.

A bakery can take hourly samples of bread loaves and plot their weight ranges on an R chart. The centerline marks the average range of weights, while control limits define acceptable variability. When sample ranges stay within these limits, the process is under control. Ranges exceeding limits indicate potential issues like equipment malfunction, prompting immediate corrective measures.

R charts are preferable when standard deviation use is impractical or when process variations are unknown. They provide a simpler, more accessible method for tracking variability within subgroups without requiring complex statistical calculations. This makes R charts particularly valuable in real-world manufacturing and quality control settings where quick, reliable monitoring is essential.

Data points outside control limits on an R chart indicate that process variability has exceeded expected boundaries, suggesting external disruptions or process anomalies. This signals the need for investigation to identify root causes such as equipment failures, material changes, or operator errors. Prompt corrective action helps restore process stability and maintain product quality.