Use a G chart when you want to monitor the number of opportunities or, in many cases, the number of days between rare events, such as infections or surgical complications.

When you monitor rare events with a traditional attribute chart, such as a P or a U chart, you need a large amount of data to establish accurate control limits. Therefore, collecting enough rare event data to detect an adverse change in the frequency of events may take months or even years. You do not need to collect large amounts of data to use a G chart. The G chart is based on the geometric distribution. The G chart plots the number of opportunities between events so you can easily detect when events occur more often than expected.

In some situations, the actual number of opportunities between events is not known. Instead, the dates of the events are recorded. When you use the G Chart in these situations, you should verify that the number of possible opportunities per day is fairly constant.

A hospital wants to monitor the number of post-surgical infections to ensure that the rate of infection remains low over time. Hospital staff record the date of each post-surgical infection. Because this data is rare event data, the staff use a G chart to track the rate of infections.

Data: Infections.MTW (available in the Sample Data folder).