Quality Improvement Zone

It is a line graph showing a measure in chronological order, with the measure on the vertical (y) axis, and time or observation number on the horizontal (x) axis. 

The median of the data points (the middle value) is added once 10 or so data points are available.  Changes made to a process, and other useful annotations, are also often marked on the graph so that they can be connected with the impact on the process.

Run charts are one of the most useful tools in quality improvement. They allow us to:

• Look at our data over time to assess performance and see whether there are any patterns
• Assess and show whether changes are resulting in improvement
• Monitor measures, to see whether improvement has been sustained

Sometimes, just by plotting your data over time, you can start to see patterns and understand more about what is going on in your system. 

If you have at least 10-12 data points, there are four simple run chart rules you can use to help you assess whether there is any non-random variation present:

• A trend (5 or more points in the same direction)
• A shift (6 or more points on one side of the median)
• More, or fewer, runs than would be expected
• An astronomical data point.

These rules are explained in more detail here.

For your initial run chart looking at a measure, especially with historical or baseline data, you would calculate the median across all your data points.  When doing improvement, it is often helpful to freeze and extend your baseline median, to help to detect a change sooner.  

For example, the chart in the picture below has the median for the first 13 points extended across the rest of the chart.  A clear shift in the data can be seen compared with that baseline median.

If you don’t have baseline data from before your project started, you can use your judgement as to whether it’s appropriate to create a baseline median from the first 10 or so data points – depending upon what you know about when change has happened. 

Creating a run chart

Run charts can be created fairly simply in Excel or by plotting a line chart that contains the data and the calculated median. More information on how to produce a run chart in Excel is available here.