in 30 minutes
Anne Ku
15 September 2005
Diagram
Decision nodes & alternatives Chance nodes & probabilities Outcomes Expected values Rolling back Perfect and imperfect information
Examples
Decisions only - no uncertainty Uncertainties only - no decision Roll of dice, flip of a coin Imperfect information: test, sample, rumour, hire consultant Perfect information: perfect foresight, clairvoyant
Expected Value
Also known as weighted average (as all the probabilities add to one) Multiply each outcome of an uncertain alternative by its probability, then Add the results together Expected value criterion: choose the alternative with the highest or lowest expected value (depending on whether more is better, or less is better)
R&D Funding
GM was evaluating two competing technologies in their engine development program. One used a new type of coating (Project A), while the other incorporated a new material (Project B). Project A had been going on for some time when Project B was identified. While they could be researched simultaneously, the two technologies offered the same benefits and could not be implemented together. The decision alternatives were therefore:1. Continue with Project A only 2. Stop Project A and start Project B 3. Do both 4. Cease Project A and not do Project B.
Applications
Medical, healthcare, pharmaceutical Energy Business Manufacturing Litigation: sue, claim, mediation R&D investment Drug research Drilling for oil Product planning Product development Capacity planning Applying for a job, graduate school, project proposal EXAMPLES
Exercises
Draw a decision tree at the time when you were applying to get into college. Which colleges did you apply? What were your chances? Assign values. Draw a decision tree for job hunting Draw a decision tree for choosing a date Draw a decision tree for travelling