UPI Study › Courses › Foundations of Leadership › Free lessons › Lesson 7.2 Free with a free account
Decision Analysis
Foundations of Leadership · Chapter 7: Decision-Making ModuleSection 7.2 · lesson 39 of 9011 min · free with a free account
Free preview
Create a free account to keep watching
It takes a minute and costs nothing. Your free account unlocks all of Chapter 1 and 3 more lessons of Foundations of Leadership.
Lesson complete
Earn the 3 college credits for Foundations of Leadership
Enrolling adds a quiz after each lesson, the graded work and the official transcript. Recommended for credit by NCCRS.
Next lesson: Seven Steps to Effective Decision Making →← From Problem to DecisionNext lesson: Seven Steps to Effective Decision Making →
In this lesson
A method that does not replace judgement - it forces judgement to state itself.
- Name the four building blocks of any decision problem
- Read a decision tree and roll it back
- Compute expected monetary value and state its limits
- Judge when the method is the wrong tool
Free study notes
Get this lesson's notes by email
The key points and 4 practice questions with answers, in your inbox. One email, free.
One email. Unsubscribe in one click.
Transcript
Everything said in the video, section by section (1,446 words). Read along, or search it.
Decision-Making Module
Decision Analysis
High stakes, several alternatives, and a future nobody can pin down. That combination is where intuition quietly stops being reliable. Decision analysis is the first quantitative toolkit for that situation. It is worth being clear about what it does not do. It does not replace judgement. It disciplines judgement. By forcing decision-makers to state alternatives, identify possible futures, attach probabilities, and quantify outcomes. All in a single coherent frame. The frame is the contribution. Not the number that comes out of it.
The Discipline
Four Questions, Answered Explicitly
At its core, decision analysis answers four questions in sequence. What can I choose? What might happen? How likely is each possibility? And how much do I value each outcome? Each question becomes an explicit input. That is the whole trick, and it is easy to underrate. Making an assumption explicit means somebody else can argue with it. So the enduring output of a decision analysis is not a single number. It is a transparent record of the reasoning that produced that number.
Origins
Where the Method Came From
The intellectual roots run deeper than the business application suggests. Probability theory, from the seventeenth century. And utility theory, developed by Daniel Bernoulli, John von Neumann, and Oskar Morgenstern. Modern decision analysis was assembled in the post-war period. By Howard Raiffa, Ronald Howard, and others at Harvard and Stanford. Raiffa codified it in nineteen sixty-eight, in Decision Analysis, Introductory Lectures on Choices Under Uncertainty. The method grew out of the operations-research community of the nineteen fifties and sixties. It is now standard in capital budgeting, pharmaceutical research, energy planning, and public policy. But its appeal to business is blunter than the mathematics implies. When a decision will spend hundreds of millions of dollars, or commit a firm for years. The discipline of writing the assumptions down is itself valuable. Regardless of whether the final calculation turns out to be exact.
The Distinction
Probability Is Not Preference
There is one confusion that undoes more decision analyses than any error of arithmetic. Conflating probability with preference. Probability is how likely something is. Preference is how much we want it. Decision analysis insists on keeping them apart. Here is why that matters. Take a ten per cent chance of a one hundred million dollar payoff. And a fifty per cent chance of a twenty million dollar payoff. Both have the same expected value. They have completely different risk profiles. A risk-averse decision-maker may rationally prefer the second one. Even though the two look identical in expectation. Utility theory is the formal machinery for separating those two judgements. So that each one can be debated on its own terms, rather than smuggled inside the other.
Building Blocks
Every Problem Decomposes the Same Way
Every decision-analysis problem decomposes into the same four elements. Alternatives are the courses of action under consideration. Building a new plant, leasing capacity, or outsourcing. States of nature are the uncertain conditions under which each alternative plays out. Strong demand, moderate demand, weak demand. Probabilities are the decision-maker's best estimates of how likely each state is. And payoffs are the values that result from each alternative and state combination. Usually monetary, sometimes utility-adjusted. Together those four populate either a decision matrix, or a decision tree. Chance nodes become expected values. Decision nodes become the best available choice.
The Matrix
A Capacity-Expansion Choice
Take a concrete capacity-expansion choice. Three alternatives. Build a large plant, build a small plant, or lease capacity. Three states of nature, with probabilities attached. Strong demand at zero point four. Moderate demand at zero point four. Weak demand at zero point two. The large plant returns ninety crore rupees under strong demand. Thirty crore under moderate demand. And it loses forty crore under weak demand. The small plant returns fifty, thirty-five, and ten crore across the three states. Leasing returns thirty, twenty-five, and fifteen crore. Look at the bottom of each column, not just the top. They differ in expected return. They also differ in exposure.
The Tree
Built Left to Right, Solved Right to Left
The decision tree is the same information, drawn. Square nodes represent decision points. Choices the manager controls. Circular nodes represent chance events. Outcomes the manager does not control. And the end-points represent the payoffs. Now here is the part students most often get backwards. The tree is built from left to right. First you decide, then nature acts. But it is computed from right to left. Each chance node is replaced by its expected value. And each decision node is replaced by its best alternative. It yields a single recommended path through the tree. Along with the expected value of actually following it.
The Metric
Expected Monetary Value, and What It Hides
The most widely used summary statistic here is expected monetary value. It is simply the probability-weighted average of an alternative's payoffs. For the large plant, that works out to forty crore rupees. The small plant gives thirty-six crore. Leasing gives twenty-four. On that criterion alone, the large plant is the preferred alternative. But expected monetary value carries three assumptions that ride along unstated. First, it assumes the decision will be repeated many times under the same probabilities. That is a thin assumption for a one-off strategic move. Second, it is entirely silent on the spread of outcomes. It treats a sure forty crore as identical to a coin-flip between zero and eighty crore. Third, it implicitly treats the decision-maker as risk-neutral. Most decision-makers are not. Utility theory extends the method by replacing monetary payoffs with utility values. Producing the more general criterion of expected utility.
Case
When the Ranking Flipped
A case where those limits actually changed the answer. In twenty twenty-two, a renewable-energy developer in southern India chose between two wind-farm sites. Site A offered higher peak output, but greater variability in wind speed. Site B offered steadier output, at a lower level. A purely expected-value comparison favoured Site A, by roughly eight per cent. Then the analysts ran a sensitivity analysis on the wind-speed assumptions. And applied a utility adjustment for the firm's debt covenants. Those covenants penalised downside variance heavily. With both adjustments in, Site B emerged as the preferred choice. Same inputs. Fuller question. Opposite answer. Expected monetary value is a starting point, not an endpoint. And the analysis is only ever as good as the questions asked of it.
Robustness
How Fragile Is the Recommendation?
Because every input to a decision analysis is an estimate, the method builds in self-criticism. Sensitivity analysis is a systematic exploration of how the recommendation changes as inputs change. Suppose the optimal alternative flips when strong-demand probability moves from zero point four to zero point three five. That recommendation is fragile, and warrants further investigation. If instead it holds across a wide range of inputs, the analyst can be more confident. Tornado diagrams are the standard visual aid here. They rank the input variables by how much each one moves the output. Closely related is the expected value of perfect information. It is the maximum a decision-maker should be willing to pay to eliminate uncertainty about a state. The expected payoff if you knew the future state in advance. Against the expected value of the best alternative under uncertainty. In practice that gives you a ceiling. A cap on what should be spent on market research, pilot studies, or consulting reports.
In Practice
Where It Works, and Two Cautions
Decision analysis is now embedded in the strategic planning routines of several industries. In pharmaceutical research, a single Phase three trial can cost a billion dollars. So firms build elaborate trees linking technical, regulatory, and commercial uncertainties. In oil and gas, trees frame exploration choices and farm-in agreements. In public health, they compare screening policies and vaccination strategies. And in corporate strategy, the method underpins real-options valuation. Which treats a staged investment as buying the right, but not the obligation, to expand or abandon. Two cautions are worth stating plainly. First, the method works best when alternatives and states can be specified clearly. Under genuine ambiguity, its apparent precision can actively mislead. Second, it is most valuable when the analysis is opened to multiple participants. Sponsors, technical experts, and dissenters, so the assumptions can be challenged. Decision analysis run in isolation is a recipe for elegant but unowned recommendations.
Consolidate
Accepting a Lower EMV on Purpose
One final example, because it shows the method doing something counter-intuitive. In twenty twenty, Operation Warp Speed in the United States chose which vaccine candidates to fund. The underlying logic was a portfolio decision-tree problem. Each candidate had an uncertain probability of clinical success. An uncertain time to availability. And an uncertain manufacturing yield. The programme spread funding across three platforms. Messenger RNA, viral-vector, and protein-subunit. That deliberately accepted a lower expected value for each individual candidate. Lower than a concentrated bet would have produced. What it bought instead was a reduced probability that all the candidates would fail at once. Which is the honest summary of the whole method. Decision analysis succeeds when its assumptions are openly debated. And it fails when its numerical surface is mistaken for certainty.
About Foundations of Leadership at UPI Study
Foundations of Leadership (Business 205) is a self-paced online course of 90 video lessons in 12 chapters, from the roots of leadership theory and the trait, situational and transformational approaches to power, decision-making, communication, teams, conflict, diversity and global leadership. It carries a NCCRS credit recommendation for 3 semester credits.
Every lesson transcript is free on pages like this one, and the videos are free with a free UPI Study account. Enrolling adds a practice quiz after each lesson, the graded work and final exam that earn the credit, lifetime access, and an official transcript on completion. UPI Study has helped over 130,000 students with college credits. ACE and NCCRS have over 2,100 cooperating colleges that will consider accepting credits; the final decision is with the universities.
Enroll now → Course details Download the syllabus All Business courses Every course with PRO →
Compare: Management and leadership courses · Foundations of Leadership vs Leadership and OB
Why take it here
Why students take Foundations of Leadership with UPI Study
Where the credit goes
Universities that work with NCCRS
Foundations of Leadership carries a NCCRS credit recommendation. These universities work with NCCRS; some are UPI Study's signed partners. ACE and NCCRS have over 2,100 cooperating colleges that will consider accepting credits; the final decision is with the universities.
Thomas Edison State UniversitySigned partner
University of the PeopleSigned partner
Charter Oak State CollegeSigned partner
Strayer UniversitySigned partner
Columbia Southern UniversitySigned partner
Indiana TechSigned partner
Penn StateWorks with NCCRS
Southern New Hampshire UniversityWorks with NCCRS
SUNYWorks with NCCRS
+many more cooperating universitiesFind my college →Find my college → Not listed? Ask Athena in the corner of this page, or book a 15-minute call.
FAQ
Questions students ask us
About Decision Analysis
What is decision analysis in management?
How do you calculate expected monetary value?
How do you solve a decision tree?
What is the expected value of perfect information?
About the Foundations of Leadership course
How many college credits is Foundations of Leadership?
How much does Foundations of Leadership cost and what is included?
Which universities accept UPI Study credits?
How long does Foundations of Leadership take?
How are the exams done?
How do my credits reach my college?
Ready for the full course? Earn 3 credits in Foundations of Leadership.
90 video lessons, a quiz after each one, and the graded work that earns the credit. Recommended for credit by NCCRS.
3 credits · NCCRSEnroll →