In this chapter, you learned to: Define the terms state of nature, event, decision alternatives, payoff, and utility; organize information in a payoff table or a decision tree; compute opportunity loss and utility function; find an optimal decision alternative based on a given decision criterion; assess the expected value of additional information.
Trang 119 1
Trang 3Classical Statistics … focuses on estimating a parameter,
such as the population mean, constructing confidence intervals,
or hypothesis testing
Statistical
Decision Theory
… (Bayesian statistics) is concerned with determining which decision, from a set of
possible decisions, is optimal.
Trang 4…these are future events that are not under the control of the decision maker
Trang 5Expected Payoff or Expected Monetary Value
(EMV)
…is the Expected Value for each decision
Trang 6A business example A business example
Nortel is considering introducing a new wireless telecommunication device into the market.
They are considering three alternatives:
I. Build a new full scale plant for
manufacturing the new product
II. Build a medium size plantIII. Do not market the product
If they decide to market the product, the annual profit will
depend on the market response to the product.
Suppose preliminary market analysis indicates that the market response to the product may be highly favourable, moderately favourable, or unfavourable. What decision should they make?
Suppose preliminary market analysis indicates that the market response to the product may be highly favourable,
moderately favourable, or unfavourable. What decision should they make?
Trang 7Available Choices Available Choices
I Build a new full scale plant D1
II Build a medium size plant D2 III Do not market the product D3
I Build a new full scale plant D1
II Build a medium size plant D2
III Do not market the product D3
Market response to the product may be highly favourable S1 moderately favourable S2
unfavourable S3
Market response to the product may be highly favourable S1 moderately favourable S2
unfavourable S3
(S1) (S2) (S3) (D1) 400 20 800 ( D2) 80 60 50
Payoff Table Payoff Table
(Values … Millions of dollars)
Trang 9(S1) (S2) (S3) (D1) 400 20 800 ( D2) 80 60 50
NonProbabilistic Criteria NonProbabilistic Criteria
Note the minimum payoff
for each decision alternative
Trang 10NonProbabilistic Criteria NonProbabilistic Criteria
Note the maximum payoff
for each decision alternative
Note the maximum payoff
for each decision
alternative
We don’t have any information about the probabilities of the 3 states of nature, except
Payoff Table Payoff Table(Values … Millions of dollars)
Trang 11NonProbabilistic Criteria NonProbabilistic Criteria
Choose a number alpha between 0 and 1 (called the pessimisticoptimistic index)
Choose a number alpha between 0 and 1 (called the pessimisticoptimistic index)
Trang 12NonProbabilistic Criteria NonProbabilistic CriteriaThe PessimisticOptimistic Index
Trang 17Criteria Based on Opportunity Loss (Regret)
Trang 18The “best” of these “worst cases” is D2 The “best” of these “worst cases” is D2
Market Response Decision
(S1) (S2) (S3)
Trang 19Value of Perfect Information
Value of Perfect Information i.e. …what is the worth of information known in advance
under the conditions of uncertainty
Trang 20See the following Decision Tree Examples…
Trang 21(S1) (S2) (S3) (D1) 400 20 800 ( D2) 80 60 50
Decision Tree
Decision
Tree
Decision Tree Examples… Decision Tree Examples…
Trang 22Decision Tree
Decision
Tree
(S1) (S2) (S3) (D1) 400 20 800 ( D2) 80 60 50
Decision Tree Examples… Decision Tree Examples…
Trang 23(S1) (S2) (S3) (D1) 400 20 800 ( D2) 80 60 50
Decision Tree Examples… Decision Tree Examples…
Decision Tree Decision
Tree
Trang 24…and much more!
Trang 25This completes Chapter 19