13 Decision Analysis


In previous chapters, we have generally assumed that all the information we need for our models is known with certainty. When we recognized uncertainty at all, we addressed it using sensitivity analysis (as in Chapter 4). In the chapters on optimization, we tended to ignore uncertainty because Solver requires us to assume that the parameters in our models are fixed. But many business problems contain uncertain elements that are impossible to ignore without losing the essence of the situation. In this chapter, we introduce some basic methods for analyzing decisions affected by uncertainty.

In the typical spreadsheet model, there are two kinds of inputs: decisions and parameters. Decisions are subject to the control of the decision maker, whereas parameters are beyond the control of the decision maker. Whether based on judgment or derived from empirical data, parameters are usually treated as fixed—known in advance with certainty. Now, we broaden our viewpoint to include uncertain inputs—that is, parameter values that are subject to uncertainty. Uncertain parameters become known only after a decision is made.

When a parameter is uncertain, we treat it as if it could take on two or more values, depending on influences beyond our control. These influences are called states of nature, or more simply, states. In many instances, we can list the possible states, and, for each one, the corresponding value of the parameter. Finally, we can assign probabilities ...

Get Management Science: The Art of Modeling with Spreadsheets, 4th Edition now with the O’Reilly learning platform.

O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.