Guest post by John Hunter, author of the Curious Cat Management Improvement Blog.
The video shows the presentation by Ron Moen, Prediction is the Problem, at our 2012 annual conference. A previous post on our blog in 2013 included a clip from this talk and explored Ron’s thoughts which might be of interest if you enjoy this presentation.
You may benefit from reading my previous post on enumerative and analytic studies before you watch the video (if you don’t clearly understand the importance of knowing when to use analytic thinking).
use statistics to support the learning of subject matter knowledge. That was a breakthrough in the book. We were always trying to use statistics to enhance the subject matter knowledge. That was the key.
This idea seems simple and maybe unimportant but if you question how data is used in your organization you will often find it separated from subject matter knowledge. When you try to act on data alone, rather that use data to enhance your deep understanding of the specific processes and systems in your organization you can quickly misuse statistics to lead you astray.
The book he discusses in the presentation is Quality Improvement Through Planned Experimentation.
Keep the data in its rawest form… Plot the data in the order it was generated… Make changes and use the data to decide if the change was an improvement. Any sort of aggregation and sort of symmetric function, summary statistics, you lose the power of the information.
One challenge is to create a culture that expects data to be used to improve learning and decision making. However, the use of data is not sufficient. The data must be used properly and this point is much more frequently an issue than I would hope. It is important to create systems that not only encourage the use of data but do so in a way that avoids the problems so often seen without an understanding of variation, or the difference between analytic and enumerative data, or without an understanding of other risks to misuse data.
Related: How to Use Data and Avoid Being Mislead by Data – Understanding Data is Often Challenging – Stratify Data to Hone in on Special Causes of Problems – Design of Experiments: The Process of Discovery is Iterative