Signs in factories or on the back of long-range trucking rigs sometimes proclaim “X days since our last accident” or “No on-the-job injuries since 1964.” Extending the stretch between such accidents may be motivated by this announcement alone, but there are better ways to diminish or prevent rarely occuring events by using data analysis and process improvement tools.
|
ADVERTISEMENT |
Simply keeping track of tragic but rarely occuring events may seem like an ineffective way to prevent future tragedies. In fact, however, data analysis that focuses on the intervals between such events can help to diminish their recurrence by analyzing special cause and common cause variation. It can also help to evaluate whether an improvement step that has been taken is working. A statistical approach includes the use of g-charts and t-charts, control charts that are enjoying expanded application in health care and crisis management organizations.
…
Comments
Data
Dr. Cleary, Could you provide me with the raw data used for your charts?
Thanks!
smoore@wausaupaper.com
Interesting topic
Dr. Cleary,
This is a good introduction of two SPC tools that I was not familiar with. Thank you for writing it.
Could you please post references for more detailed information on the t-chart and g-chart.
Annie Dodson
Ascend Performance Materials
yes interesting topic...
I agree with Annie (comment below) - I would also like more information. I was well aware of g-charts and have used them to analyze rare events in health care improvement efforts, but I was not aware of the t-chart. According to my understanding of your article we should use the t-chart (and not the g-chart) when we are analyzing time data. Doing a quick search on g-charts it is not unusual to get information that you can use a g-chart to calculate the time or units between events, which according to your article a t-chart should be used with time data. From what I found is that a t-chart is the same formulae as the X-chart (or individuals chart) whereas the g-chart is the same formulae as the p-chart - so it makes sense to me that a t-chart should be used with time data and g-chart be used for number of nonconforming units (mislabel specimens, number of falls between patients, etc). Currently, I'm working with a resident who wants to improve the rare event of mislabeled specimens in the Emergency Department. Analyzing the number of days between errors in a g-chart shows a stable process, however placing the data into a t-chart shows one special cause. Thanks for your timely article and if you could let us know a good source to learn more about t-charts that would be helpful, Karen
Keep it Simple
The best analysis is the simplest analysis that gives you the insight you need as a basis of action for improvement. Why not plot the time between rare events on an Individuals/Moving Range chart? The data remains in context and the I/mR chart utilizes the generic and fixed 3-sigma limits found by Shewhart to be the only correct limits. The g- and t-charts inflate the upper limits unnecessarily. I have been using the I-mR chart with the four Western Electric rules with great success for many years to track rare events such as OSHA recordable injuries in industrial settings. In addition, not many software packages include g- or t-chart calculations; and I would not utilize g- or t-charts if they did. The I/mR chart is simple and requires no particular distribution. Thus data transformation (as seen in the t-chart) is unnecessary.
XmR Chart
Question: Does the XmR chart and the t-Chart tell the same story about this process?
Rich
Add new comment