Documente Academic
Documente Profesional
Documente Cultură
HEAD
TAIL
Winnings
-2
Probability
0.5
0.5
EV 4
1
1
2
2
2
EMV 10 1 10
Example 2:
A potential customer for a 50,000 fire insurance policy
has a home in an area that, according to experience, may
sustain a total loss in a given year with a probability of
0.001 and a 50% loss with a probability of 0.01. There is
a 98.9% chance that no claim will be made.
Ignoring partial losses, what premium should the
insurance company charge to break even?
Solution:
Expected Claim =
= 300
A premium of 300 would break even in the long run
Portfolio Selection
A
Economy declines
.5
-2
-7
No change
1.0
-1
Economy expands
2.5
22
DECISION THEORY
Elements of a decision problem:
1.
2.
3.
4.
Decision maker
Alternative courses of action
Events and associated probabilities
Consequences
Example:-
Concession problem
States/events
Cold weather
Warm weather
(p = 0.3)
(p = 0.7)
Action
a1 : sell cola
a2 : sell coffee
1,500
4,000
5,000
1,000
Profit (000)
Portfolio Selection
Economy declines
0.5
-2
-7
No change
1.0
-1
Economy expands
2.5
22
Portfolio Selection
A
Economy declines
2.5
7.5
No change
1.0
3.0
Economy expands
19.5
17.0
3,750
Decision trees
Nodes represent points in time
Square nodes decision points
Round nodes chance events
Arcs represent actions
Example:
An investor has a certain amount of money to invest.
Three alternative portfolio selections are available. The
estimated profits depend on the economic conditions as
follows:
Payoff matrix:
Profit (000)
Portfolio Selection
A
(0.3)
.5
-2
-7
No change (2)
(0.5)
1.0
-1
(0.2)
2.5
22
Payoffs (000)
0.5
(0.3)
2
2
3
(0.5)
(0.2)
Portfolio A
2.5
1 (0.3)
Portfolio B
1.0
2 (0.5)
- 2.0
2.0
3 (0.2)
Portfolio C
5.0
1 (0.3)
4
2 (0.5)
-7.0
-1.0
3 (0.2)
22.0
Example
An oil company must decide whether to drill (a1) or not
to drill (a2) in a particular place in the Celtic sea. The
well may turn out to be dry (1), wet (2), or soaking (3),
and on the basis of other drillings in the Celtic sea the
company believes that the probabilities for these states
are as follows:
P(1) = 0.5
P(2) = 0.3
P(3) = 0.2
The cost of drilling is $70,000. If the well turns out to be
wet the revenue will be $120,000 and if it turns out to be
soaking the revenue will be $270,000. (There is no
revenue for a dry well). Should the company drill or
not?
E(drill) = (-70)(0.5) + (50)(0.3) + (200)(0.2) = 20
E(do not drill) = 0
Therefore the company should drill