Decision Analysis
What are three characteristics of Decision Problems?
1) alternatives available 2) criteria in a decision problem 3) states of nature
Three steps of Decision Problems are:
1) decisions 2) alternatives 3) outcomes
To use the MAXIMAX in Excel, which function are you using?
=MAX
Rolling Back Procedure: at each probability node the __________ is calculated and written above the node.
EMV
To calculate the EVPI take the total expected value with perfect information and subtract the EMV
EVPI
This decision rule selects the decision alternative with the largest expected monetary value
Expected Monetary Value
MAXImizing the MAXimum is the
Maximax decision rule
A more conservative approach to decision making compared to the MAXIMAX is the
Maximin
This decision rule can be used to hedge against the worst possible outcome of a decision
Maximin
This decision rule pessimistically assumes that nature will always be against us, regardless of the decision we make
Maximin
This decision rule uses a regret matrix and shows the difference between the maximum payoff that can occur under a given state of nature, and the payoff that would be realized each alternative under the same set of nature.
Minimax
Do good decisions always result in good outcomes?
No
Monetary values in a decision tree are called
Payoffs
This procedure is a systematic way of calculating EMVs in a decision tree, and thereby identifying the optimal decision strategy
Rolling Back Procedure
Decision trees can be used for any decision problem, but they are particularly useful for more __________ problems
complex
Probabilities in a decision tree are ______________ on the events that have already been observed (events to the left)
conditional
Maximin (_________________ criteria)
conservative
The maximin decision criteria is called the _______________ approach
conservative
Hiring a consulting, test market study, seismic testing are all examples of
contingent decisions
____________ decisions generally require a test or analysis to be done and then await for the ________ of the test which would give a better indication of the results of the next decision.
contingent, results
To do this, you must have some idea of what the future might hold, and a good understanding of the _______ & ___________ of the possible outcomes.
costs, benefits
A _________________ node represents a choice to be made (square)
decision
Decision Trees are composed of nodes and branches. What are three nodes of the decision tree?
decision, events and terminals
Branches leading out of a decision node represent the posible
decisions
An __________ node (circle) represents a "state of nature" or something that happens
event
another word for reward and costs are
gains, losses
A ____________ form known as decision tree can also represent decision problems
graphical
Although the alternative suggested by the maximax decision rules enables one to realize the best possible payoff, it does not ________________ that this payoff will occur.
guarantee
The key characteristic of the MAXIMAX criteria for making decisions is:
high reward and high risk
Many decision problems represent one-time decision for which _____________ data for estimating probabilities are unlikely to exist.
historical
The MAXIMAX decision criteria is appropriate for large companies and not for startups because
in the worst case scenario, companies still lose alot of money, and there is high risk/uncertainty involved with the outcomes.
In a decision tree, time proceeds from _____ to _____
left, right
Probabilistic decision rules can be used if the states of nature in a decision problem can be assigned probabilities that represent their _____________ of occurrence.
likelihood
The key characteristic of the Maximin criteria for making decisions is that there is
low reward, low risk
Perfect Information always gives the ________ value of each probability column
maximum
The Maximax decision rule determines the best (___________) payoff in each row (alternative) of the payoff table and then selects the alternative with the largest payoff
maximum
Another way of approaching decision problems involves the concept of regret, or ____________ _______
opportunity loss
Maximax ( ______________ criteria)
optimistic
The Maximax decision rule is often called the ________________ approach
optimistic
For decision problems that occur more than once, it is often possible to estimate these ________________ from historical data.
probabilities
Branches leading out of _____________ nodes (events) represent the possible outcomes of uncertain events; the decision make has no control over which of these will occur.
probability
Minimax _________
regret
To use the minimax regret decision rule, we must first convert our payoff matrix into a ______________ __________ that summarizes the possible opportunity losses that could result from each decision alternative under each state of nature.
regret matrix
Positive payoffs correspond to _______________ and negative payoffs correspond to ____________
rewards, costs
You can't predict the future. But you can be smart about how you manage in the face of _______ & _______________
risk, uncertainty
The key to success is using data and common sense to take smart risks, and to strike a balance between downside _______ and upside ________.
risks, reward
The EMV for a given decision alternative indicates the average payoff we would receive if we encounter the identical decision problem repeatedly and always _________ this alternative.
select
Rolling Back Procedure: At each decision node, the alternative with the best EMV is
selected
Market demand (not under our control) is an example of a
states of nature
It is reasonable to expect good outcomes to occur more frequently when using a ___________ approach to decision making than if we make decisions in a more haphazard manner.
structures
The MAXIMAX criterion is only appropriate when the decision maker can
survive even the worst case payoff
A ______________ node (triangle) indicates the problem is completed - all decisions have been made.
terminal
You make the best decision based on your analysis and the information you have at the time with the current situation but :
you may not have all of the information, uncertainty/risk can change