How to Measure Anything: Finding the Value of Intangibles in Business, 3rd Edition

CHAPTER 6 Quantifying Risk through Modeling

It is better to be approximately right than to be precisely wrong.

—Warren Buffett

We’ve defined the difference between uncertainty and risk. Initially, quantifying uncertainty is just a matter of putting our calibrated ranges or probabilities on unknown variables. Subsequent measurements reduce uncertainty about the quantity and, in addition, quantify the new state of uncertainty. As discussed in Chapter 4, risk is simply a state of uncertainty where some possible outcomes involve a loss of some kind. Generally, the implication is that the loss is something dramatic, not minor. But for our purposes, any loss will do.

Risk is itself a quantity that has a lot of relevance on its own. But it is also a foundation of further measurement for decision making. As we will see in Chapter 7, risk reduction is the basis of computing the value of a measurement, which is in turn the basis of selecting what to measure and how to measure it. Remember, if a measurement matters to you at all, it is because it must inform some decision that is uncertain and has negative consequences if it turns out wrong.

This chapter discusses a basic tool for almost any kind of risk analysis and some surprising observations you might make when you start using this tool. But first, we need to separate from this some popular schemes that are often used to measure risk but really offer no insight.

How Not to Quantify Risk

What many organizations do to assess risk is ...