Making Decisions on Purpose, Explained with Examples

UPI Study › Courses › Quantitative Analysis › Free lessons › Lesson 5.1 Free with a free account

Making Decisions on Purpose

Quantitative Analysis · Chapter 5: Decision Analysis with ProbabilitiesSection 5.1 · lesson 20 of 5512 min · free with a free account

← Queue Design and EconomicsNext lesson: Data That Informs Choices →

Earn 3 college credits for Quantitative AnalysisRecommended for credit by NCCRS · Math 250 · self-paced · one payment, lifetime access
Enroll in Quantitative Analysis · $250 →Download the syllabus (PDF)

In this lesson

A formal methodology for structuring, analyzing, and resolving complex business decisions.

  • Contrast intuitive decision-making with structured decision analysis
  • Identify alternatives, states of nature and payoffs in a real problem
  • Build a payoff table and choose the objective that resolves it
  • Tell single-stage from multi-stage decisions, and test robustness

Transcript

Everything said in the video, section by section (1,683 words). Read along, or search it.

Decision Analysis with Probabilities · Section 5.1

Making Decisions on Purpose

Welcome to section five point one, Making Decisions on Purpose. This opens the chapter on decision analysis. Every manager makes decisions, and most of them barely register. What to put on tomorrow's agenda. Whether to approve a small expense. But some decisions differ in kind, not merely in size. Entering a new market. Choosing between two major capital projects. Those are too consequential to leave to gut feel alone. Decision analysis is the formal method for structuring decisions like those. It does not replace your judgment. It disciplines it. By the end you will build a payoff table, and know why it never decides for you.

Two Modes

Intuition Is Fast. It Is Also Fragile.

Let us start by being fair to intuition. Intuition is fast, it is cheap, and it is often correct. That holds especially for decisions a manager has made many times before. The tenth time you price a routine job, your gut is a trained instrument. The trouble is the other kind of decision. High stakes, and infrequent. There you have no practice, and intuition has well documented weaknesses. It is sensitive to mood, to anchoring, to recency, and to overconfidence. Set the two modes side by side, and the contrast is sharp. The intuitive mode leaves assumptions implicit, and is hard to reproduce or audit. The structured mode makes assumptions explicit, and can be defended line by line. It is slower upfront. On average, it produces better outcomes.

What Structure Buys

Three Advantages Worth the Extra Time

Three advantages of the structured approach deserve emphasis. First, assumptions are made explicit. Every probability, every cost estimate, every payoff gets written down. That sounds like paperwork. It is really conflict resolution. When assumptions stay hidden, two managers argue about the conclusion and get nowhere. Written down, the disagreement becomes concrete, and therefore resolvable. Second, the analysis is reproducible. Another analyst, given the same inputs, reaches the same recommendation. The reasoning can be audited, reviewed, and challenged. Third, consistency under pressure improves. When time is short and emotions run high, a pre-built model prevents panic-driven reversals.

Anatomy

Every Decision Problem Has Three Blocks

Every formal decision problem has three building blocks. Spotting them inside a messy real situation is the first practical skill here. The first block is the set of decision alternatives. These are the things you can actually choose, and they are under your control. The second block is the states of nature. These are the things that might happen, and they sit outside your control. Demand turns out strong, or moderate, or weak. You do not get a vote. The third block is the payoffs, the consequence of one alternative meeting one state. Those three blocks still do not give you a recommendation. An optimisation method does that, by maximising expected value, minimising cost, or maximising utility.

The Components

What We Choose, What We Cannot

Let us pin down each component, because this vocabulary runs through the whole chapter. Decision alternatives are mutually exclusive courses of action the decision-maker may choose. Mutually exclusive means you pick exactly one of them. By convention they are written a one, a two, and onward to a m. States of nature are the uncertain outcomes that affect the result. They must be mutually exclusive, and collectively exhaustive. Collectively exhaustive means the list covers every possibility, with nothing left over. Leave a state off, and your model quietly proceeds as though it cannot happen. By convention these are written s one, s two, and onward to s n. Payoffs are the numerical consequence for each alternative and state pair. Usually money, sometimes utility. They are neither chosen nor suffered, but determined by the model.

The Payoff Table

The Canonical Workspace

Now arrange the components into a payoff table. This is the canonical workspace of decision analysis, and the conventions are universal. Rows are the decision alternatives, columns are the states of nature, and each cell holds one payoff. Take a small factory expansion. Expand a lot, expand a little, or do nothing. The states are strong demand, moderate demand, and weak demand. The large expansion earns two hundred and fifty thousand dollars if demand is strong. But it loses ninety thousand if demand turns out weak. The small expansion gives up the top end, earning one hundred and forty thousand dollars at best. But it never loses money, and under moderate demand it actually beats the large one. Doing nothing earns zero everywhere, which is exactly why it belongs in the table. Read down a column to see how every alternative fares under one state. Read across a row instead, and you see the whole range one alternative can produce. The large expansion spans three hundred and forty thousand dollars, best case to worst. The small expansion spans just one hundred and thirty thousand. That gap is the risk you are buying.

The Objective

The Table Does Not Decide For You

The payoff table by itself does not tell you what to choose. It is raw material. Choosing an alternative requires a numerical objective, and three answers are common. First, maximise expected monetary value, usually shortened to E M V. That is the probability-weighted average of the payoffs across all states. It suits repeated, financially scaled decisions, where averages matter more than individual swings. Second, minimise cost. Same logic, with negative payoffs. That fits procurement, logistics and operations, where revenue is fixed and only cost moves. Third, maximise utility, using a function that captures risk aversion. Very large losses are penalised more heavily than equivalent gains are rewarded. E M V is the default in most business courses and applications. But when one bad outcome could threaten the firm's survival, that default breaks. A choice that maximises E M V while risking bankruptcy is irrational, however high its average return.

One Stage Or Many

Some Decisions Buy Information

Some decisions are single-stage. You choose once, and you live with it. Should we accept this contract, at this price? The answer does not change afterwards. Many real business decisions are nothing like that. They unfold in sequence. An early choice determines which later choices are even available to you. Consider whether to run a pilot study before a full launch. Or whether to buy a small stake that creates an option on the rest. The pilot costs money and time, and it guarantees nothing. What it changes is the information you hold when the second decision arrives. So you are not only choosing an action. You are choosing what you will know. Decisions like that are modelled with decision trees.

Tree Conventions

Squares Choose, Circles Happen

A decision tree has two kinds of node, and the shapes are not decorative. Square nodes represent decisions the manager makes, and branches from a square are alternatives. Circular nodes represent chance events, and branches from a circle are states of nature, each labelled with a probability. Nobody picks those. The world picks. Terminal nodes at the right show the final payoff for each path through the tree. Trees are solved by backward induction, and the direction genuinely matters. At each chance node, compute the expected monetary value. At each decision node, take the branch with the highest E M V. The recommendation then reads forward, from the root. Multi-stage analysis also reveals something called the value of information. That is the difference in E M V between deciding now, and deciding after a study. If that value exceeds the cost of the study, the study is worth doing.

Robustness

Would the Answer Survive Being Wrong?

A recommendation is only as good as the inputs that produced it. So the last discipline in this section is sensitivity analysis. It asks one question. If our estimates are wrong, does the recommendation change? An answer that holds across a wide range of inputs is robust. An answer that flips, when a probability moves from zero point four to zero point five, is fragile. Fragile is not the same as wrong. It means the answer deserves more scrutiny first. A tornado chart ranks the inputs by how far each one moves the answer, widest bar on top. In this example the market share assumption dominates, then unit price, then variable cost. Discount rate and project lifetime barely move the answer at all. So spend your effort at the top, leave the bottom rough, and report the robustness, not only the answer. Alternative A stays recommended across market shares from fifteen to thirty-five per cent. That is a far stronger statement than simply saying A is recommended.

Practical Application

Build a Payoff Table for Harbour Point

Time to put this to work. Harbour Point Development Group is a mid-size real-estate developer. It is evaluating three projects for the next building cycle. Project P one is luxury condominiums. High build cost, high upside, vulnerable in soft markets. P two is mixed-use commercial and residential, with balanced upside and downside. P three is affordable rental apartments. Low cost, modest upside, resilient even in poor markets. Four market conditions are plausible. A boom, steady growth, a mild recession, and a deep recession. Build a three by four payoff table, with plausible estimates in millions of dollars. Be explicit about build cost, sale price per unit, and absorption rate in each condition. Then classify every cell as certain, risky, or uncertain. Risky means probabilities can be estimated. Uncertain means they cannot. Find the project with the highest maximum payoff, and the one with the highest minimum. An optimist takes the first, a pessimist the second. Ask why the firm might want neither. Finally, name the three inputs you trust least. Those are your sensitivity candidates.

Section Summary

Structure First, Then the Numbers

Let us gather the section into one place. Decision analysis is a formal methodology, and it earns its keep in three ways. It makes assumptions explicit, it is reproducible, and it holds steady under pressure. Every decision problem has the same three components. Alternatives, which we choose. States of nature, which we cannot control. And payoffs, the consequence of each combination of the two. A payoff table arranges them. Rows are alternatives, columns are states, cells are payoffs. It is the raw material, not the recommendation. An objective turns it into one. Maximise E M V, minimise cost, or maximise utility. Single-stage decisions are made once. Multi-stage decisions unfold, and are drawn as trees. A square means a decision, a circle means a chance event. Sensitivity analysis asks whether the recommendation survives being wrong about the inputs. Next section adds the missing ingredient. Probabilities on the states of nature.

About Quantitative Analysis at UPI Study

Quantitative Analysis (Math 250) is a self-paced online course of 55 video lessons in 13 chapters, from decision analysis and simulation to inventory and queuing models, project scheduling, linear programming and transportation models. 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 Math courses Every course with PRO →

Compare: Statistics vs Quantitative Analysis

Why take it here

Why students take Quantitative Analysis with UPI Study

Decide with numbersQuantitative Analysis teaches the models managers use to decide under uncertainty: decision trees, simulation, inventory and queuing models, project scheduling and linear programming. It is part of many business, management, operations and supply-chain programs.
Credit at a fraction of the priceThe same 3 credits can cost $750 or more at a US college. Here it is one payment, self-paced, with lifetime access.
Finish your degree soonerTransfer credits reduce the courses you still owe, so you can graduate earlier or lighten a heavy semester.
Strengthen an applicationA completed college-level course on an official transcript shows admissions and scholarship committees you can do the work.
Study on your own scheduleNo start dates, no deadlines. Watch the lessons, practice, and take the final when you are ready.
130,000+students helped with college creditsACE and NCCRS have over 2,100 cooperating colleges that will consider accepting credits; the final decision is with the universities.

Where the credit goes

Universities that work with NCCRS

Quantitative Analysis 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 UniversityThomas Edison State UniversitySigned partnerUniversity of the PeopleUniversity of the PeopleSigned partnerCharter Oak State CollegeCharter Oak State CollegeSigned partnerStrayer UniversityStrayer UniversitySigned partnerColumbia Southern UniversityColumbia Southern UniversitySigned partnerIndiana TechIndiana TechSigned partnerPenn StatePenn StateWorks with NCCRSSouthern New Hampshire UniversitySouthern New Hampshire UniversityWorks with NCCRSSUNYSUNYWorks 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 Making Decisions on Purpose

What are decision alternatives, states of nature, and payoffs?
Decision alternatives are the mutually exclusive actions a decision-maker can choose, such as expanding a factory a lot, a little or not at all. States of nature are uncertain outcomes outside the decision-maker's control, such as strong, moderate or weak demand; they must be mutually exclusive and collectively exhaustive. Payoffs are the numerical consequences, usually money, of each alternative meeting each state.
How do you read a payoff table?
A payoff table lists alternatives as rows, states of nature as columns, and payoffs in the cells. Reading down a column shows how every alternative fares under one state; reading across a row shows the full range one alternative can produce. For example, a large expansion ranging from $250,000 to a $90,000 loss spans $340,000, far riskier than a small one spanning $130,000. The table itself does not choose.
When should a decision-maker maximize utility instead of expected monetary value?
Maximize utility instead of EMV when one bad outcome could threaten the firm's survival, using a utility function that penalizes large losses more heavily than equal gains. EMV suits repeated, financially scaled decisions where averages matter more than individual swings. A choice that maximizes expected value while risking bankruptcy is irrational, however high its average return. Cost-minimization is the third common objective, used when revenue is fixed.
What is the difference between single-stage and multi-stage decisions?
A single-stage decision is made once and then lived with, such as accepting a contract at a given price. A multi-stage decision unfolds in sequence, where an early choice, like running a pilot study, shapes the later options and the information available. Multi-stage problems are modeled with decision trees, and they reveal the value of information: if a study adds more expected value than it costs, it is worth doing.

About the Quantitative Analysis course

How many college credits is Quantitative Analysis?
Quantitative Analysis (Math 250) carries a NCCRS credit recommendation for 3 semester credits. ACE and NCCRS have over 2,100 cooperating colleges that will consider accepting credits; the final decision is with the universities.
How much does Quantitative Analysis cost and what is included?
$250, paid once, with lifetime access: all 55 video lessons, a practice quiz after each, the graded work and final exam, and an official transcript when you finish. Students who want several courses choose UPI Study PRO instead.
Which universities accept UPI Study credits?
UPI Study has signed partner agreements with universities such as Thomas Edison State University, University of the People and Charter Oak State College, and works with universities such as Penn State, SNHU and SUNY. ACE and NCCRS have over 2,100 cooperating colleges that will consider accepting credits; the final decision is with the universities. Use "Find my college" on this page to check yours.
How long does Quantitative Analysis take?
It is self-paced with no deadlines. The 55 lessons total about 11 hours of video; most students add reading and practice time and finish in a few weeks to a few months, on their own schedule.
How are the exams done?
Quizzes and assignments are online in the course. The final exam is taken online with proctoring; a person on the UPI Study team checks assignments, usually within two days.
How do my credits reach my college?
When the course shows 100% complete, request the official transcript from your dashboard. It is sent to the college you name, and you can send it to more than one. Check your college first with "Find my college" on this page, or ask Athena.

Ready for the full course? Earn 3 credits in Quantitative Analysis.

55 video lessons, a quiz after each one, and the graded work that earns the credit. Recommended for credit by NCCRS.

Enroll in Quantitative Analysis →Download the syllabusEvery course with PRO →
Quantitative Analysis
3 credits · NCCRSEnroll →