I've been presenting at the Institute for Healthcare Improvement (IHI) annual forum for 21 consecutive years. Maybe the biggest surprise from these two decades has been the awesome power of simply "plotting the dots," i.e., plotting important organizational data in their naturally occurring time order. I have evolved to using fewer, simpler tools in my consulting and have never been more effective.

My all-day course at the forum demonstrated this with a wide variety of data from real situations. I showed how the power of this simple philosophy could be the back door through which improvement practitioners could educate their managers and executives in the best possible way—by getting eye-opening results. I also emphasized the need to learn and use common-cause strategies, which are not generally taught. All this requires very few tools, but it does require a total change in mindset regarding improvement. I'm not comparing myself to Deming, but I realized that he was always criticized for the virtual lack of tools taught in his seminars. Twenty years of hard study has made me evolve to a similar approach to improvement.

During my recent travels speaking at conferences and consulting, root cause analysis (RCA) seems to have taken on a life of its own and is now a well-established subindustry in any organization, regardless of its chosen approach to improvement.

There are many things that “shouldn’t” happen. Why not consider such incidents as undesirable variation and get back to basics? One of Deming’s principles was that there are two kinds of variation—common cause and special cause—and that treating one as the other makes things worse.

And the human tendency is to treat virtually all variation as special cause—of which RCA is another example.

Has anyone considered whether things that “shouldn’t” happen might be common cause—as in, one’s organization is “perfectly designed” to have them occur? What might be the effect of multiple RCAs in such cases?

‘Because we worked so hard!’

I was at a conference where one of the poster sessions proudly declared that they had reduced infections in a pediatric unit. It used the following display:

My last article demonstrated a common incorrect technique—based in “traditional” statistics—for comparing performances based on percentage rates. This article will use the same data to show what should be done instead.

To quickly review the scenario: In an effort to reduce unnecessary expensive prescriptions, a pharmacy administrator developed a proposal to monitor and compare individual physicians’ tendencies to prescribe the most expensive drug within a class. Data were obtained for a peer group of 51 physicians including the total number of prescriptions written, and, of that number, how many were for the target drug.

My last column, “Dealing With Count Data and Variation,” showed how a matrix presentation of stratified count data could be quite effective as a common-cause strategy. I’ll use this column to review some key concepts of count data as well as to demonstrate the first of two common statistical techniques that can be useful for further analysis. Obtaining the counts themselves is only half of the job.

First, make sure the operational definition is clear: What’s the threshold whereby something goes from a “nonincident” (i.e., a value of 0) to an “incident” (i.e., a value of 1)? Would two or more people assessing the situation concur that the “incident” had occurred?

In addition, all count data have an implicit denominator that’s defined by the “area of opportunity” for that count. It depends on what's being counted, how it’s being counted, and what possible restrictions there might be upon the count.