Practical Tableau

Chapter 43. How to Make a Control Chart

Control charts, or Shewhart charts, were designed to evaluate whether production is in a state of statistical control. Along with Pareto charts, histograms, and scatter plots, they are one of the seven basic tools for quality control. Basic control charts show a time-series analysis with reference lines that show the average performance along with an upper control limit, typically three standard deviations above the mean, and lower control limit, typically three standard deviations below the mean.

Control charts were originally called Shewhart charts, named for Walter Shewhart, who invented the visualization type while working on a way to improve the reliability of the telephony transmission systems at Bell Labs in the 1920s. Control charts were born in, and are still primarily used for, evaluating manufacturing processes. For example, a factory may use this type of analysis to predict production levels and have a statistical indicator for when corrective action needs to be taken.

How to Make Control Charts in Tableau

While designed for manufacturing, I find control charts to be useful for any measure in which historical data can be used to predict performance and provide visual cues for when a statistically significant change is occurring in the business. In that vein, and so we can all follow along using the same data, this tutorial will create a basic control chart that evaluates the Profit Ratio measure in the Sample - Superstore dataset. ...