About an year and a half ago, I was struggling with a measurement problem. Being a Six Sigma Black Belt it was clear that in order to make sustainable process improvements, I need to quantify process performance and establish a sound measurement system around it. In a continuous physical process, where you are making a product or part, it can be done relatively easily. But in a transactional environment it is not easy to normalize a measurement and establish a simple, yet sound metric.Concept of Measurement:
Measurement is a set of observations that reduce uncertainty where the result is expressed as quantity. Note that the uncertainty has to be quantified, but the subject of observation might not be a quantity itself.
Object of Measurement:
Using a short series of connections, called Clarification Chain, we can see intangibles becoming tangibles:
1. If it matters at all, it is detectable/observable.
2. If it is detectable, it can be detected as an amount (or range of possible amounts)
3. It it can be detected as a range of possible amounts, it can be measured.
Four Useful Assumptions:
1. Your problem is not as unique as you think.
2. You have more data than you think.
3. You need less data than you think.
4. There is a useful measurement that is much simpler than you think.
These concepts sound very theoretical, but will become more clear in the context, once you read the book and the accompanied text. Whenever, I get into the measurement quandary I think of these things and it helps me to look at my problem in an entirely new light. In my experience, most important of these are the four useful assumptions. In a normal day-to-day business operation, I come across so many situations, where "we have no data" is the "root cause" of the "problem" we are seeing. Come on, that can't be possible. Look at all the data/IT systems we have built around us in last 10 years. I force my thinking as "we gotta have this data somewhere"!
And this is how I now look at my measurement related problems.










