Earlier in this series I introduced the topics of Process Capability and Process Control. You may wish to review that article before reading this one.
I recently received the following query from one of my Green Belt students:
“In my company our manufacturing process has a lot of special variations which makes the process very unpredictable. This causes a lot of deviations and that is where most of our resources are directed, since we need to close these deviations in order to release the lots. My question is where do I start? I have a feeling that we would need a whole Six Sigma deployment to fix these issues, but given the current situation what can I do to at least to start quantifying these things and trying to improve some of these issues?”
I wrote the following reply: You stated that the process has “….a lot of special variations” but I wonder if you have any proof to back up that statement. Unfortunately, the concept of special cause vs. common cause variation in a product or process is foreign to most organizations. Most have no idea which type of variation they are dealing with, and as a result they make wrong decisions about what course of action is appropriate.
I would begin by doing some Pareto analysis and identifying the highest priority issues in terms of cost and/or customer dissatisfaction. I would next determine whether special cause or common cause variation is present using either run charts or (preferably) control charts. If special cause variation is present, then the problem is temporary or transient in nature and we need to identify and correct the special cause(s). If common cause variation is present, then the variation is inherent and ongoing and we must change the product or process in order to make improvement.
One wrong decision is treating special cause variation as if it is common cause. We spend time and money changing the product or the process, when what we should be doing is identifying and eliminating the special cause(s). For example, assume we are working for a company that makes televisions. Some of our customers are reporting that the picture on a particular model of television is pixelated and erratic. We launch a project to redesign the TV, when the root cause of the problem is in fact a weak signal from the cable company at the customer location – a special cause. We spend a lot of time and money on the redesign, but we don’t correct the problem.
The other wrong decision is treating common cause variation as special cause variation. We spend time and effort chasing non-existent special causes when we should be redesigning the product or process. Assume that all of the sets of a particular television model have an unsatisfactory picture, and the root cause of the problem lies with the fundamental design of the set. We are told by the leadership of our organization to get busy looking for a special cause (that does not exist), and we spend a lot of time and effort doing so. Or worse, we start changing things without knowing the root cause, hoping that one of the changes is the “silver bullet” that corrects a non-existent special cause. No amount of looking for a special cause is going to correct the problem if one does not exist.
We must take precautions to avoid both of these types of mistakes. We must identify the root cause of the problems and issues, and must chose an appropriate course of action based on whether the variation due to that root cause is special cause or common cause. If there is a special cause, then we should first correct that special cause and then reevaluate to see if the output is now acceptable to the customer. If the problem remains after all special causes are eliminated – i.e. the variation is common cause and is inherent in the product or process – then we need to take further action to revamp the product or process in order to improve the output.
Your comments or questions about this article are welcome, as are suggestions for future articles. Feel free to contact me by email at firstname.lastname@example.org.
About the author: Mr. Roger C. Ellis is an industrial engineer by training and profession. He is a Six Sigma Master Black Belt with over 48 years of business experience in a wide range of fields. Mr. Ellis develops and instructs Six Sigma professional certification courses for Key Performance LLC. For a more detailed biography, please refer to www.keyperformance.com.