SPC Charts

Add to favourites

Statistical Process Control (SPC) Charts are simple graphical tools that enable process performance monitoring.

What is it?

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 average of the data is shown as the centre line.   Sigma limits are also shown, which are calculated based on a measure of variation in the data (sigma).  These limits show what range we can expect most future data points to be in based on the variation seen in the data if the process is stable and therefore predictable.

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.

There are different types of SPC chart depending on the type of data you have.  The most common ones are:

  • P chart – for classification data expressed as a % or proportion
  • I chart (or Xmr chart) – for individual measurements
  • C chart – count data – for numbers of incidents (or U chart if expressed as a rate)
  • Xbar & S chart – for measurements data where an average can be calculated at each time point

You can find more about the different charts in the Health Care Data Guide.  The types of data are described more in the topic on developing your measures.

What does this tool look like?
Example of SPC Chart
Why use this tool?

Use an SPC chart when you want to:

  • Understand your data over time using a more powerful tool than a run chart
  • Differentiate between common cause and special cause variation (see understanding variation topic – insert link)
  • Assess whether your process is stable and therefore predictable, or unstable and unpredictable
  • Understand whether your process is capable of a desired level of performance
Where does this tool fit in the improvement journey?


This tool is relevant at this stage of the Quality Improvement Journey.

How to use it

Make sure you know what type of data your measure is that you are going to plot.  It’s important you use the right type for your data so that the right assumptions are made in the calculations.  If in doubt, use an I chart – although this is the least powerful of the charts for detecting special cause.

Don’t create an SPC chart with fewer than 12 data points (20 for an I chart) – use a run chart instead. Also consider the control limits temporary until you have more than 20 data points.

SPC charts can be created in excel, and commercial add-ons such as QI charts or QI macros can be purchased to help with this.  Dedicated SPC software is also available.  Alternatively, an excel template is available for download here: http://www.isdscotland.org/Health-Topics/Quality-Indicators/Statistical-Process-Control/

There are five rules you can use to help you assess whether there is any special cause variation present:

API Rules for detecting special cause

Note that when your measure has different denominators over time, e.g. in an Xbar & S chart, p chart or u chart, the control limits will vary.

Use your charts to understand whether the changes you are making are resulting in improvement. For your initial SPC chart for a measure, especially with historical or baseline data, you would calculate the mean and control limits across all your data points.  When doing improvement, it is often helpful to freeze and extend your baseline mean, to help to detect a change sooner.   However, you would only do this if there were no special causes present in your baseline data.  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 from the first 12-20 data points – depending upon what you know about when change has happened. 

The understanding variation topic page explains more about reacting appropriately to common and special cause variation.