Run Chart
Time-series chart with median line and runs tests — the pre-analysis for a control chart, without any spread assumption.
Also known as: run chart, runs chart
A run chart plots a data series in time order with a median line but no control limits. Instead of ±3σ, four formal runs tests check the randomness of the order:
- Clustering — too few runs about the median (points bunch on one side; level shift)
- Mixtures — too many runs about the median (points cross too often; two overlaid sources)
- Trends — too few up/down runs (long monotone streaks; drift, wear)
- Oscillation — too many up/down runs (zig-zag; controller over-correction)
See also
Used in
In the Algorithm Lab
Sources
- Provost, L. P. & Murray, S. K. — The Health Care Data Guide: Learning from Data for Improvement, Jossey-Bass, 2011
- Anhøj, J. & Olesen, A. V. — Run Charts Revisited: A Simulation Study of Run Chart Rules for Detection of Non-Random Variation in Health Care Processes, PLoS ONE, 9(11), 2014
- Montgomery, D. C. — Introduction to Statistical Quality Control, 8th Edition