13.2 Dealing with uncertainty in decision making Flashcards
Tools available when probabilities are not available
- Maximax rule
- Maximin rule
- Minimax regret rule
Maximax rule involves
- Selecting the alternative that maximises the maximum payoff achievable
- The maximum payoff is selected for each option and the maximum of those is chosen (max of max)
- Suitable for optimist who aims to achieve the best result if the best happens
Maximin rule involves
- Selecting the alternative that maximises the minimum payoff achievable
- The minimum payoff is selected for each option and the maximum of those is chosen (max of min)
- Suitable for pessimist who aims to achieve the best results if worst happens
Minimax regret rule
- Minimises the maximum regret
- It is useful when probabilities for outcomes are not available or if investor wants to avoid making a bad decision (wrong)
- Regret here is defined as the opportunity loss from making wrong decision
To find the minimax regret
- Find the maximum payoff in each demand row (what we could have earned if right decision was made)
- For each level of supply compare the actual payoff (what we did earn) with what we could have earned, difference is the regret
- Create a regret table with values in
- Determine the maximum regret for each supply level
- Choose supply level which produces the minimum of those values
Perfect information is produced if
- All possible outcomes of a decision can be predicted with 100% certainty therefore forecast of future outcomes is always correct
- Having access to perfect info means decision makers will always make the right choice, enabling them to maximise profits or minimise costs
- Info can be made more perfect if additional info is obtained (eg research)
Imperfect information
- The forecast is usually correct, but can be incorrect
- It is not as valuable as perfect info
The value of perfect info can be calculated as
Expected profit (outcome) WITH the info
Minus
Expected profit (outcome) WITHOUT the info
A decision tree is a
- Diagrammatic representation of a decision problem, where all possible courses of action are represented, and every possible outcome of each course of action is shown
- They should be used where a problem involves a series of decisions and several outcomes
- It may involve joint probabilities where the outcome of one event depends on outcome of preceding event
Drawing decision trees
Step 1 - Draw the tree from left to right showing appropriate decisions and events / outcomes. Label the tree and cash inflow/outflows and probabilities associated with outcomes
* Squares represent decision point where course of action must be chosen
* Circles are used at chance outcome points and the branches from here are always subject to probabilities
Step 2 - Evaluate the tree from right to left carrying out two actions:
* Calculate an EV at each outcome point
* Choose the best option at each decision point
Step 3 - Recommend a course of action to management
The main benefit of a decision tree is
- That it maps out clearly all the decisions and uncertain events and how they are interrelated
- They are especially useful where the outcome of one decision affects another decision
- However suffers from same limitations and expected values
Other factors to take into account when considering decision tree type problems
- Assumes risk neutrality - Some decision makers don’t choose options which give greatest expected value because they are risk seekers or risk averse
- Sensitivity analysis - The analysis depends on the values of probabilities in tree which are subjective estimates and open to question. Sensitivity analysis can be used to consider break even positions for each variable (ie value at which decision would change)
- Oversimplification - In order to make tree management the situation has to be simplified which makes it appear more discrete than it is. In practice it is more likely that outcomes would for a near continuous range of inflows and outflows
Using sensitivity analysis to stress test decision making
- Sensitivity analysis takes each uncertain factor and calculates the change that would be necessary to reverse the original decision
- This can help determine which variables are more critical than others in affecting a decision
Strengths of sensitivity analysis
- Info will be presented to management in a form which facilitates subjective judgement to decide the likelihood of various possible outcomes considered
- It identifies areas which are crucial to the success of the project and which should be carefully monitored
Weaknesses of sensitivity analysis
- It assumes that changes to variables can be made independently
- It only identifies how far a variable needs to change it doesn’t look at probability of change
- It provides info on basis of which decisions can be made but doesn’t point to correct decision directly
