Statistical Thinking – Revisited

On February 4, 2010, we posted a blog piece, Statistical Thinking Part 1. It is funny, we debated whether the topic was important and relevant in today’s business environment. We believed it was or the piece would neither have been written nor posted.

In the last week of June, I got the latest issue Quality Engineering in the mail. As usual, I turned to the table of contents to see which if any articles piqued my interest. I was delighted to see the lead article “Statistical Thinking and Methods in Quality Improvement: A Look to the Future” by Roger W. Hoerl and Ron Snee. This keynote article was followed by four commentary pieces reacting to the main article. All of a sudden, we felt more on the cutting edge than ever.

The tones of our piece versus the scholarly tone in the Quality Engineering Journal are exactly that. Our piece on this blog was general, looking for a workable definition of Statistical Thinking that should be conveyed to all business and engineering students. We were exploring and advocating a mindset that people should possess and could rely on in any situation, independent of the ability to do much more than find the arithmetic average of a column of numbers.

One of the official definitions of Statistical Thinking we used in our previous blog posting was:

Statistical Thinking is a philosophy of learning and action based on the following fundamental principles:

1. All work occurs in a system of interconnected processes


2. Variation exists in all processes


3. Understanding and reducing variation are keys to success

This definition came from a paper co-authored by Lynne Hare, Roger W. Hoerl, and Ron Snee. Clearly, Mssrs. Hoerl and Snee have been thinking quite a bit about Statistical Thinking.

The gist of their latest paper is that statistics needs to be more of an engineering discipline than a pure science. The world is getting so complicated with an incredible amount of data available at our fingertips through a myriad of on-line sources, statistical skills will be more and more important as we have a need to make actionable information out of this mass or morass of data. They believe that professional statisticians have to move from the academic to the practical and from the abstract to the applicable. Statisticians have to enable companies to make better decisions, more often, and faster.

At Cadent Resources, Inc. this is exactly how we endeavor to operate. We are engineers and statisticians. We take the wealth of supply and demand chain data available in companies big and small and turn it into actionable meaningful information. We try to present the data and the analyzed data into forms and formats that help planners plan more effectively. We use the information to trigger appropriate actions and perhaps more importantly, when to not over react and simply let the plan in place handle the common cause variation.

It is good to be on the cutting edge.