Run charts revisited: a simulation study of run chart rules for detection of non-random variation in health care processes

• Published in: PloS one Vol. 9; no. 11; p. e113825
• Main Authors: Anhøj, Jacob, Olesen, Anne Vingaard
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 25.11.2014; Public Library of Science (PLoS)
• Subjects: Ambulatory care; Binomial distribution; Charts; Computer and Information Sciences; Control charts; Data points; Delivery of Health Care; Drift; Engineering and Technology; Health care; Medicine and Health Sciences; Models, Organizational; Normal distribution; Physical Sciences; Research and Analysis Methods; Signal processing; Simulation; Statistical analysis; Statistical tests; Denmark
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0113825

A run chart is a line graph of a measure plotted over time with the median as a horizontal line. The main purpose of the run chart is to identify process improvement or degradation, which may be detected by statistical tests for non-random patterns in the data sequence. We studied the sensitivity to shifts and linear drifts in simulated processes using the shift, crossings and trend rules for detecting non-random variation in run charts. The shift and crossings rules are effective in detecting shifts and drifts in process centre over time while keeping the false signal rate constant around 5% and independent of the number of data points in the chart. The trend rule is virtually useless for detection of linear drift over time, the purpose it was intended for.