# Chapter 8: Decision analysis

decision analysis
an analytic and systematic approach to the study of decision making.
good decision
based on logic, considers all possible alternatives, examines all available information about the future and applies decision modeling approach
not based on logic, does not use all available information, does not consider all alternatives, and dost not use appropriate decision modeling techniques
1. define problem
2. list alternatives
3. identify possible outcomes
4. list payoffs
5. select and apply decision analysis model
5 steps of decision making
decision alternative
a course of action or strategy that can be chosen by the decision maker
outcomes (state of nature)
an occurrence over which the decision maker has little or no control.
We will write a custom essay sample on
Any topic specifically for you
For only \$13.90/page
payoffs
outputs or conditional values
payoff table (decision table)
easiest way to present payoff values
decision making under certainty, uncertainty, and risk
three decision-making environments
decision making under certainty
decision makers know for sure the payoff for every decision alternative; typically there is only one outcome for each alternative. future outcomes are known
decision making under uncertainty
decision makers have no information at all about the various outcomes; they do not know the likelihood that a specific outcome will occur. several outcome can occur.
decision making under risk
decision makers have some knowledge regarding the probability of occurrence of each outcome. several outcomes can occur as a result of a decision or alternative, probabilities of the outcomes are known.
maximax (optimistic)
selects the decision alternative that maximizes the maximum payoff over all alternatives; locate max payoff for each alternative and select alternative with highest payoff.
maximin (pessimistic)
finds the alternative that maximizes the minimum payoff over all decision alternatives; locate min payoff for each alternative and select alternative with highest payoff.
criterion of realism (Hurwicz)
offers a compromise between optimistic and pessimistic decisions. also called weighted average criterion
coefficient of realism
measures the decision maker’s level of optimism regarding the future; denoted by alpha with a value between 0-1.
equally likely (Laplace)
finds the decision alternative that has the highest average payoff; first calculate average payoff for each alternative and pick the alternative with max avg payoff. places an equal weight on all outcomes
regret criterion
based on opportunity loss- the difference between the optimal payoff and the actual payoff received.
minimax regret
finds the alternative that minimizes the maximum opportunity loss within each alternative
loss table
determines the opportunity loss of not choosing the best alternative for each outcome
EMV (expected monetary value)
computed as the weighted average of all possible payoffs for that alternative, where the weights are the probabilities of the different outcomes.
average actual
EMV represents the long-run _____ payoff, while the _____ payoff from a decision is listed in the decision table
EOL (expected opportunity lost)
computed as the weighted average of all possible regrets for that alternative, where the weights are the probabilities of the different outcomes
minimum
the _________ EOL will always result in the same decision alternative as the maximum EMV.
perfect information
certain and is never wrong
EVwPI (expected value with perfect information)
the expected payoff with perfect information before a dedcision has been made.
EVPI (expected value of perfect information)
EVwPI – Maximum EMV
decision tree
consists of nodes and arcs, just like a network. presents the decision alternatives and outcomes in a sequential manner
decision table
a table in which decision alternatives are listed down the rows and outcomes are listed across the columns. the body of the table contains the payoffs.
decision node
have arcs (lines) that denote all decision alternatives available to the decision maker at that node. of these, the decision maker must select only one alternative.
outcome node
have arcs that denote all outcomes that could occur in that node. of these, only one outcome will actually occur.
folding back
the process by which a decision tree is analyzed to identify the optimal decision
expected payoff
computed at each outcome node using the probabilities of all possible outcomes at that node and payoffs associated with those outcomes
alternative
computed at the decision node that yields the better expected payoff
certainty equivalent
the minimum gauranteed amount one is willing to accept to avoid the risk associated with a gamble
conditional value
a consequence or payoff, normally expressed in a monetary value, which occurs as aresult of a particular alternative and outcocme
efficiency of sample information
a ratio of the expected value of sample information and the expected value of perfect infromation
EVSI (expected value of sample information)
the average or expected value of imperfect or survey information
opportunity lost
the amount you whould lose by not picking the best alternative. for any outcome, this is the difference between the consequences of any alternative and the best possible alternative. also called regret
outcome
an occurrence over which the decision maker has little or no control. also known as state of nature.
risk avoider
a person who avoids risk. as the monetary value increases on the utility curve, the utility increaes at a decreasing rate. this decision maker gets less utility for a greater risk and higher potential returns.
risk nuetral
a person who is indifferent toward risk. the utility curve for a risk-neutral person in a straight line.