Decision Analysis + Bayes Rule

_________________ decisions generally require a test or analysis to be done and then wait for the results of the test which would give a better indication of the results of the next decision

Contingent

The most we would pay for perfect information is translated in the

EV of PI

Larger firms should use the ________________ decision rule

MAXIMAX

This decision rule has high reward but also high risk

Maximax

This decision rule can be used to hedge against the worst possible outcome of a decision. Pessimistically assumes that nature will be against us.

Maximin

This decision rule has low reward but also low risk

Maximin

Another way of approaching decision problems is using opportunity loss (regret).

Minimax

The set of strategies available to a decision maker is known as the

alternatives

If the value of the sensitivity analysis for the probability of a state of nature was +/- 0.05 to the original change point, we may want to spend money on a ________ ___________ __________, because we would not be confident with our decision given the probability.

better market analysis

Alternatives, Criteria and States of Nature are ________________ of decision problems

characteristics

MAXIMIN is often known as the ____________ criteria

conservatives

_________ in a decision problem represents various factors that are important to the decision maker and are the basis for making decisions about the alternatives

criteria

A square in a decision tree represents a

decision node

In a payoff matrix, what are the four pieces of information given

decision, alternatives, states of nature, payoff values

A circle in a decision tree represents a

event node (state of nature)

Good decisions do not always result in

good outcomes

To convert a matrix to a regret matrix, take the _____ of each column, and use this max and subtract each payoff value from the max.

max

In a MAXIMAX decision rule, take the ______ of the rows of the alternatives, and take the _____ of those row values

max, max

Name three non-probabilistic methods of decision rules

maximax, maximin and minimax

In a regret matrix, when the subtractions have been done, we select the ________ of each row alternative, and then select the ________ of each row values

maximum, minimum

In a MAXIMIN decision rule, take the _______ of the rows of alternatives, and take the _____ of those row values

min, max

MAXIMAX is often known as the ____________ criteria

optimistic

Probabilistic decision rules can be used if the states of nature in a decision problem can be assigned _______________ that represent their likelihood of occurence

probabilities

When making decisions, the key to success is using data and common sense to take smart risks, to strike a balance between downside ________ and upside __________

risk, rewards

You can't predict the future. But you can be smart about how you manage decisions in the face of _____ & _____________

risk, uncertainty

It is important to accompany any decision analysis with a ______________ ______________ as a key component of the analysis.

sensitivity analysis

______________ ____ ________ in a decision problem correspond to future events that are not under the decision maker's control

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 different manner

structured

The maximax criterion is appropriate when the decision maker can

survive even the worst payoff

A triangle in a decision tree represents a

terminal node (end of decision)