What Is Decision Analysis? Decision Analysis In A Nutshell

Stanford University Professor Ronald A. Howard first defined decision analysis as a profession in 1964. Over the ensuing decades, Howard has supervised many doctoral theses on the subject across topics including nuclear waste disposal, investment planning, hurricane seeding, and research strategy. Decision analysis (DA) is a systematic, visual, and quantitative decision-making approach where all aspects of a decision are evaluated before making an optimal choice.

Understanding decision analysis

Fundamentally, decision analysis enables organizations to evaluate or model the potential outcomes of various decisions so they can choose the one with the most favorable outcome. The tool assesses all relevant information and incorporates aspects of training, economics, psychology, and various management techniques.

Another part of decision analysis requires the business to examine uncertainty around a decision. Uncertainty is measured by probability. In other words, what are the chances the outcome will occur? From this point, the organization can make a decision based on the value and likelihood of success of a decision. Alternatively, it can base the decision on the likelihood of failure and its corresponding impact. 

Decision analysis is extremely valuable in the project planning stage and during periodic reviews of project progress by senior management. Since most projects are characterized by decisions made with high uncertainty, decision analysis has multiple applications. For one, the analysis helps project teams obtain accurate activity duration estimates. Decision analysis also assists in risk analysis, “what-if” analysis, and subproject terminating in a research and development context. 

How does decision analysis work?

The decision analysis process can be explained in the following steps.

1 – Identify the problem 

What is the problem to be solved or the decision to be made? 

Once this has been determined, a list of possible options should be devised. For instance, a non-profit that receives a large endowment may have several ways they can put the money to good use. 

2 – Research options 

Each choice or option must then be researched, with any relevant data set aside to develop a decision model later in the process. Data may be quantitative or qualitative, depending on the context. 

It is important to consider each outcome in terms of its costs, risks, benefits, and probability of success or failure. 

3 – Create a framework

To allow the business to properly assess its options, an evaluation framework must be created. 

One way to achieve this is by using key performance indicators (KPIs) to measure and indicate progress. For example, a business looking to expand may stipulate that each potential new market causes a minimum increase in monthly sales volume.

Like the research from the previous step, KPI data may be qualitative or quantitative.

4 – Develop a decision model

Now it is time to combine the framework with a decision model. One of the most popular decision analysis models is the decision tree, where each choice has branches representing different outcomes. 

Influence diagrams can also be used when there is a high amount of uncertainty around a decision or goal.

5 – Calculate the expected value

The expected value (EV) is the weighted average of all potential decision outcomes. To calculate the expected value, multiply the probability of each outcome occurring by the resulting value – sometimes referred to as the expected payoff. Then, sum the expected values for each decision.

For example, consider a large architectural firm that designs stadiums. During a public tender process, the firm submits two designs which the city council must evaluate for viability. For the sake of this article, we will call them Design A and Design B.

The city council determines that Design A, once completed, has a 55% chance of a $350 million valuation and a 25% chance of a $275 million valuation. The expected value of Design A is (0.55 x 350,000,000) + (0.25 x $275,000,000) = $261.25 million

On the other hand, Design B has a 20% chance of being valued at $400 million and a 60% chance of being valued at $290 million. The expected value of Design B is (0.20 x 400,000,000) + (0.60 x 290,000,000) = $254 million. 

In this instance, the council should choose Design A.

Key takeaways:

  • Decision analysis is a systematic, visual, and quantitative decision-making approach where all aspects of a decision are evaluated before making an optimal choice.
  • Decision analysis is used in the project planning stage and during periodic reviews of project progress by senior management. The approach is especially suited to project management where there is often uncertainty around decision outcomes.
  • Decision analysis occurs via five steps: identify the problem, research options, create a framework, develop a decision model, and calculate the expected value. At the heart of this process are the decision tree framework and the calculation of expected value.

Connected Business Concepts

Conceptual modeling is the process of developing an abstract model or graphical representation using real-world concepts or ideas. During conceptual modeling, various assumptions are made regarding how the system functions. Conceptual models also illustrate the dominant processes in a system and how they are linked. These processes may include factors known to drive change in the system, or they may encompass the consequences of change in the factors themselves.
Constructive controversy is a theory arguing that controversial discussions create a good starting point for understanding complex problems. A constructive controversy discussion is performed by following six steps: organize information and derive conclusions; presenting and advocating decisions; being challenged by opposing views; conceptual conflict and uncertainty; epistemic curiosity and perspective-taking; and reconceptualization, synthesis, and integration.
Contextual inquiry is a research method based on user-centered design (USD) and is part of the contextual design methodology. Contextual inquiry as a research method does not involve setting people certain tasks. Instead, users are observed while they work in their own environments. The context of these environments typically encompasses the home, office, or somewhere else entirely.
Convergent thinking occurs when the solution to a problem can be found by applying established rules and logical reasoning. The term convergent thinking was first described by American psychologist Joy Paul Guilford in 1950. The process of convergent thinking involves finding the single best solution to a problem or question amongst many possibilities. 
Divergent thinking is a thought process or method used to generate creative ideas by exploring multiple possible solutions to a problem. Divergent thinking is an unstructured problem-solving method where participants are encouraged to develop many innovative ideas or solutions to a given problem. These ideas are generated and explored in a relatively short space of time. 
First-principles thinking – sometimes called reasoning from first principles – is used to reverse-engineer complex problems and encourage creativity. It involves breaking down problems into basic elements and reassembling them from the ground up. Elon Musk is among the strongest proponents of this way of thinking.
The ladder of inference is a conscious or subconscious thinking process where an individual moves from a fact to a decision or action. The ladder of inference was created by academic Chris Argyris to illustrate how people form and then use mental models to make decisions.
The Six Thinking Hats model was created by psychologist Edward de Bono in 1986, who noted that personality type was a key driver of how people approached problem-solving. For example, optimists view situations differently from pessimists. Analytical individuals may generate ideas that a more emotional person would not, and vice versa.
Second-order thinking is a means of assessing the implications of our decisions by considering future consequences. Second-order thinking is a mental model that considers all future possibilities. It encourages individuals to think outside of the box so that they can prepare for every and eventuality. It also discourages the tendency for individuals to default to the most obvious choice.
Lateral thinking is a business strategy that involves approaching a problem from a different direction. The strategy attempts to remove traditionally formulaic and routine approaches to problem-solving by advocating creative thinking, therefore finding unconventional ways to solve a known problem. This sort of non-linear approach to problem-solving, can at times, create a big impact.
Moonshot thinking is an approach to innovation, and it can be applied to business or any other discipline where you target at least 10X goals. That shifts the mindset, and it empowers a team of people to look for unconventional solutions, thus starting from first principles, by leveraging on fast-paced experimentation.
Tim Brown, Executive Chair of IDEO, defined design thinking as “a human-centered approach to innovation that draws from the designer’s toolkit to integrate the needs of people, the possibilities of technology, and the requirements for business success.” Therefore, desirability, feasibility, and viability are balanced to solve critical problems.
The CATWOE analysis is a problem-solving strategy that asks businesses to look at an issue from six different perspectives. The CATWOE analysis is an in-depth and holistic approach to problem-solving because it enables businesses to consider all perspectives. This often forces management out of habitual ways of thinking that would otherwise hinder growth and profitability. Most importantly, the CATWOE analysis allows businesses to combine multiple perspectives into a single, unifying solution.

Main Free Guides:

Scroll to Top