Mastering Designed Experimentation



Mastering Designed ExperimentationIf you've already begun your journey as an experimenter, have you found yourself asking, "What comes next?"  Maybe you have received your Six Sigma Green Belt or Black Belt certification and achieved some level of success, but still have questions. Or maybe you've run some experiments with inconclusive results or felt like you've had to solve the same problem more than once. Finally, maybe you are considering the possibility of pursuing a Master Black Belt and want to get an idea of what commitment that involves and what new skills you'll develop.

In this follow-up to my previous blog, Entering the World of Designed Experimentation, we will continue the conversation as I build a case for additional learning and practice in these experimental methods to hone your skills.

I'm a believer that experience is a very good teacher. Applying tools successfully over time will help you overcome any shortcomings and better understand the nuances of each tool. In addition to this, those who participate in training are exposed to further concepts and tools and are able to practice scenarios that may be outside of your industry to widen your experiences and capabilities. You'll still be challenged to think critically through a problem to find a solution.

The well-known statisticians George Box, J. Stuart Hunter and William Hunter have been quoted as saying, "Two…investigators…would typically begin from different starting points, proceed by different routes, and yet could reach [an equally good] answer.”  One way to interpret this idea is that a more experienced experimenter with a wider toolbox could reach that equally good answer maybe a little faster. The good news is that in most cases, there's more than one approach that can answer your project questions.

With the additional knowledge and capabilities provided by training and experience, it becomes easier for experimenters to avoid common mistakes and reach answers more efficiently. For example, one common mistake I’ve noticed many new Six Sigma Belts make is the mistreatment of noise within an experiment. Noise often can hide the factor effects we're trying to uncover if not dealt with properly. In these situations, experimenters may come to some sort of conclusion along the lines of, "I spent the resources to run this experiment, but there were no statistically significant factors – what do I do now!?" 

Utilizing the 4-axis of noise, we can chart a path during the planning phase for what noise strategies would be most appropriate for a given scenario. You could begin by answering the question, are you even completing a planning phase in the first place? Are you utilizing standard work, like an experimental planning form, to help make sure you've fully thought through the design structure of your experiment? What is the objective of this particular design? Are you just looking for active effects or are you trying to optimize? Those would require drastically different designs. 

Another important planning tool would be drawing multiple factor relationship diagrams to fully consider the noises and unit structure of your experiment and weigh different design options. Here, you also should consider: What level of disruption to production will this design involve? Are there options available to learn about a process without causing too much disruption to making customer-acceptable product? It's this initial work in the planning phase which helps us create a question-answering experiment rather than just having an "experience."

If you feel that you're not as strong in some of these areas as you'd like to be, I encourage you to join us for our Advanced Design of Experiments course at The Center. If you feel some of these topics are a little too advanced and you want to ease into your designed experiments journey, our Introduction to Design of Experiments course might be more appropriate. Regardless, if you’d just like to add to the conversation, please feel free to contact me on LinkedIn or at


Anthony WelshAnthony Welsh, Six Sigma Master Black Belt
Anthony Welsh is a Six Sigma Master Black Belt with 20 years of experience delivering projects to both the automotive and consumer products industries. In his role at The Center, Anthony shares expert tools in critical thinking and data-driven decision making to assist clients with using Six Sigma methods to achieve real results.



Since 1991, the Michigan Manufacturing Technology Center has assisted Michigan’s small and medium-sized businesses to successfully compete and grow. Through personalized services designed to meet the needs of clients, we develop more effective business leaders, drive product and process innovation, promote company-wide operational excellence and foster creative strategies for business growth and greater profitability. Find us at


Categories: Continuous Improvement, Six Sigma