# MSL 5080, Methods of Analysis for Business Operations

Unit Lesson Starting with this unit, you will blend a newly acquired (or refreshed) grasp of mathematics that supports analysis with some ideas and reflections on making decisions. The first idea you may note with interest in Chapter 3 of the textbook is what statisticians consider a good or bad decision. Certainly results count, as many leaders have, no doubt, reminded many statisticians who support them with analysis. Even so, decisions by gut instinct will, sooner or later, lead to results that are detrimental to the organization—this is what probabilities over a range of situations show. In the U.S. Army, there is a saying among leaders that “hope is not a method,” communicating that the public taxpayers are poorly served if military leaders rely on chance and optimism to succeed rather than on methodical steps taken to achieve a goal. If a good decision is a decision logically reached after considering analysis results—even those as simple as looking at coin tosses—then it follows that a bad decision is one not based on science and reason, even if luck brings fortunate results. It is a natural fact that luck for all of us runs out from time to time, and that there can be costs associated with “bad” luck. Accordingly, continue to champion good decision-making even if the odds go against the analysis predictions and the results of such a decision may occasionally be undesirable. The Six Steps in Decision-Making When you review the commonly-agreed steps of good decision-making, you can test support of good decisions by showcasing the commonly agreed upon steps (Render, Stair, Hanna, & Hale, 2015):

1. Define the problem. Everything else will be in error or under dispute if the real problem is not precisely determined and agreed upon. Among other hazards, you may waste time later finding a precise answer to a different problem than the one facing you. 2. List the possible alternatives. Feasible courses of action are listed here and not necessarily just the ones you personally hope for. Remember that doing nothing is a possible alternative. 3. Identify the possible outcomes or states of nature. Possible outcomes range from the best possible, or most optimistic, to the worst possible—and the worst possible outcome may happen, or the organization may face an unusual opportunity with the best possible outcome turning up as real. 4. List the payoff/profit of each combination of alternatives and outcomes. This can be a list or a table. 5. Select a mathematical decision theory model to use for this problem. 6. Apply the model (solve the equation) and consider the solution, then make a decision. You can wargame your own decision here to test that it is rational by asking: why did you decide what you did? Would you encourage another leader to make the same sort of decision given the calculated decision theory model results? These reflections help you focus on using logic and reason, not a gut feeling. On pages 66–67 of the textbook (including Table 3.1) you are walked through the decision-making example of the Thompson Lumber Company. See how decision-making steps are manifested in this realistic example: UNIT V STUDY GUIDE Decision Analysis MSL 5080, Methods of Analysis for Business Operations 2 UNIT x STUDY GUIDE Title Step 1: John T.’s problem was whether or not to manufacture and sell backyard storage sheds—an addition to his product lines. Step 2: Once the right problem is described, developing the possible alternatives is key to selecting the correct mathematics function and the solution for a decision. Ensuring that all feasible alternatives are considered is key. Intentional or unintentional bias may leave out the alternative that is best for the organization. Here, John’s alternatives list becomes: (a) invest in a large plant to make the shed; (b) invest in a small plant; (c) do not do anything with sheds. Step 3: For his calculations, John has to match possible outcomes for each alternative. He designated two: a favorable ma