Eric Budd’s presentation at the 2016 Annual Deming Institute Conference: An Exercise in Operational Definition.
The exercise Eric uses in the presentation shows how much variation can show up in data – just from how the data is collected. And in this example the data even has an operational definition used in collecting the data. Most data used in business does not have operational definitions known to both those collecting the data and those using it.
The variation in the data from this example also shows the importance of iteration. Iteration allows people to gain a shared understanding of how to collect the data (even when this isn’t written into a formal operational definition). And as this exercise shows even an operational definition should be iterated over before you believe the data generated by the process. How often do you validate the data collection process is working as expected before accepting the data generated by the process?
Related: Operational Definitions and Data Collection – An operational definition is a procedure agreed upon for translation of concept into measurement of some kind. by W. Edwards Deming – W. Edwards Deming: There is No True Value – Dangers of Forgetting the Proxy Nature of Data