Decision Analysis¶
Decision Analysis vs Flexibility Analysis¶
Due to this, flexibility analysis is preferred over decision analysis
-
Decision analysis
-
assumes you can define choices to take at any stage
-
Implies focus on a few distant choices
-
Flexibility analysis
-
encourages to explore
- What decisions to take
and
- When to take them
-
as granular as required
Outcome¶
-
Strategies for altering choices as future is revealed, not a unique āoptimal choiceā
-
āSecond bestā choices which offer
-
Insurance against downside
- Opportunity to exploit upside
āSecond bestā strategies are sub-optimal for each outcome, but preferable as they offer flexibility to do well in a range of outcomes. It is never the best, but never the worst
- Education of client about distribution, range of possible results (Value at Risk)
Motivation¶
People acting intuitively deal poorly with complex, uncertain situations. They
- Process probability info poorly
- Over-simplify complexity & alter reality
- Focus on extremes
- Focus on end states, not whole process
Decision analysis helps overcome this
Characteristics¶
- Assumes that every decision in the set of choices is discrete
- Looks over several time periods
- Deals with uncertainties
- Standard method
- Can include utility assessment (such as levels of consumer satisfaction)
Decision Tree¶
- Structure
- Decision points: Choices
- Chance points (possible outcomes) after each decision
- Data
- Value of each possible outcome
- Probability
- Uncertainties
Goal: Maximize expected value of outcomes
For each set of alternatives, calculate expected value. Then choose alternative with maximum EV