Analysis Under High Uncertainty

At times an organization may wish to evaluate a project about which there is little information. Research and development projects sometimes fall into this general class. But even in the comparative mysteries of research and development activities, the level of uncertainty about the outcomes of R & D is not beyond analysis. As we noted when discussing Dean's profitability model, there is actually not much uncertainty about whether a product, process, or service can be developed, but there can be considerable uncertainty about when it will be developed and at what cost.

As they are with R&D projects, time and cost are also often uncertain in other types of projects. When the organization undertakes projects in which it has little or no recent experience—for example, the installation of a new computer, investment in an unfamiliar business, engaging in international trade, and a myriad of other projects common enough to organizations in general but uncommon to any single organization—there are three distinct areas of uncertainty. First, there is uncertainty about the timing of the project and the cash flows it is expected to generate.

Second, though not as common as generally believed, there may be uncertainty about the direct outcomes of the project—that is, what it will accomplish. Third, there is uncertainty about the side effects of the project, its unforeseen consequences.

Typically, we try to reduce such uncertainty by the preparation of pro forma documents. Pro forma profit and loss statements and break-even charts are examples of such documents. The results, however, are not very satisfactory unless the amount of uncertainty is reflected in the data that go into the documents. When relationships between inputs and outputs in the projects are complex, Monte Carlo simulation 134, 651 can handle such uncertainty by exposing the many possible consequences of embarking on a project. Risfe analysis is a method based on such a procedure. With the great availability of microcomputers and user-friendly software, these procedures are becoming very common.

Risk Analysis

The term risk analysis is generally credited to David Hertz in his classic Harvard Business Review article, "Risk Analysis in Capital Investment" |27|. The principal contribution of this procedure is to focus the decision maker's attention on understanding the nature and extent of the uncertainty associated with some variables used in a decision-making process. Although the method can be used with almost any kind of variable and decision problem, risk analysis is usually understood to use financial measures in determining the desirability of an investment project.

Hertz i28] differentiates risk analysis from both traditional financial analysis and more general decision analysis with the diagrams in Figure 2-4. Figure 2-4a illustrates traditional financial analysis. Figure 2-4b risk analysis. The primary difference is that risk analysis incorporates uncertainty in the decision input data. Instead of point estimates of the variables, probability distributions are determined or subjectively estimated for each of the "uncertain" variables. With such inputs, the probability distribution for the rate of return (or NPV) is then usually found by simulation. The decision maker not only has probabilistic information about the rate of return and future cash flows but also gains knowledge about the variability of such estimates as measured by the standard deviation of the financial returns. Both the expectation and its variability are important decision criteria in the evaluation of the project. For an example, see the Reading at the end of this chapter.

When most managers refer to risk analysis, they are usually speaking of what Hertz and Thomas call "decision analysis." As Figure 2-4c shows, for decision analysis the manager's "utility function" for money must be determined. If the decision maker is seeking a decision that achieves several different objectives simultaneously, this method (utilizing a weighted factor scoring model, for example, rather than simulation) would be appropriate.

This approach is useful for a wide range of project-related decisions. For example, simulation risk analysis was used to select the best method of moving a computer to a new facility |64|. The major task elements and their required sequences were identified. Cost and time distributions were then programmed for analysis and a computer run of 2000 trials was made, simulating various failures and variations in cost and time for each of three methods of moving the computer. A cost-proba-

Project Management Made Easy

Project Management Made Easy

What you need to know about… Project Management Made Easy! Project management consists of more than just a large building project and can encompass small projects as well. No matter what the size of your project, you need to have some sort of project management. How you manage your project has everything to do with its outcome.

Get My Free Ebook


Post a comment