Sensitivity Analysis

Investigates how decision might change

given a change in the problem data.

What would be the impact if there is a

change in the probability values?

State of Nature Alternative Large shop Favorable Market 800,000 Unfavorable market -400,000 EMV 200,000

Small shop
Do nothing Probability

300,000
0 .5

-100,000
0 .5

100,000
0

Suppose there is a change in the probability P for favorable market. Then 1 P is the probability of an unfavorable market. Hence, EMV (large shop) = 800,000P 400,000(1 P) = 1,200,000P 400,000 * EMV(small shop) = 300,000P 100,000(1 P) = 400,000P 100,000 * EMV(do nothing) =0 *

Sensitivity Analysis
EMV 350000 300000 250000 200000 150000 100000 50000 -0.2 -0.1 O 0.1 0.2 0.3 0.4
Do nothing EMV(small shop) EMV(large shop)

The best decision is to do

0.5 0.6 0.7 P

-50000 -100000 -150000

nothing for as long as P is less than 0.25. EMV for doing nothing is equal to the EMV for small shop. When P is between 0.25 and 0.33, the best decision is to put up a small shop. When P is greater than 0.33, the best decision is to put up a large shop. The point of intersection is where the EMV for small shop is equal to the EMV for the large shop.

Bayesian Analysis
Bayes theorem allows decision makers to revise
probability values. The new probabilities can be assessed by a manager based on experience and intuition, can be derived from historical data or can be computed from other available data using Bayes theorem This theorem incorporates both the initial estimates of the probabilities as well as information about he accuracy of the information source (market survey). The approach of the theorem recognizes that a decision maker does not know with certainty what state of nature will occur.

Bayes Theorem The conditional probability of event A given that event B has occurred

P(B | A).P(A) P(A | B) P(B | A).P(A) P(B | A).P( A)

Problem 1
Peter Paul is going to help his brother who wants to open a food store. Peter Paul initially believes that there is a 50-50 chance that his brothers food store would be a success. He is considering doing a market research study. Based on historical data, there is a 0.8 probability that the marketing research will be favorable given a successful food store. Moreover, there is a 0.7 probability that the marketing research will be unfavorable given an unsuccessful food store. a. If the marketing research is favorable, what is Peter Pauls revised probability of a successful food store for his brother? b. If the marketing research is unfavorable, what is Peter Pauls revised probability of a successful food store for his brother? c. If the initial probability of a successful food store is 0.6 (instead of 0.5), find the probabilities of (a) and (b).

Problem 2
Two states of nature exist for a particular situation: a good economy and a poor economy. An economic study may be performed to obtain more information about which of these will actually occur in the coming year. The study may forecast either a good economy or a poor economy. Currently there is a 60% chance that the economy will be good and a 40% chance that it will be poor. In the past, whenever the economy is good, the economic study predicted it would be good 80% of the time. The other 20% of the time the prediction was wrong. In the past, whenever the economy is poor, the economic study predicted it would be poor 90% of the time. The other 10% of the time the prediction was wrong. a. Using Bayes theorem, find the following probabilities: P(good economy|prediction of good economy) P(poor economy|prediction of good economy) P(good economy|prediction of poor economy) P(poor economy|prediction of poor economy) b. Suppose the initial probability of good economy is 70% and the probability of a poor economy is 30%. Find the posterior probabilities in (a) using these new values.

Utility Theory
The overall value of the result of a decision is

called utility. Rational people make decisions that maximize the expected utility. EMV is not always the best approach. Thus, one way to incorporate attitudes toward risk is by the use of utility theory. Utility assessment assigns the worst outcome a utility of 0 and the best outcome, 1. When a decision maker is indifferent, the expected utilities are equal.

Standard Gamble for Utility Assessment

P Best outcome Utility = 1 Worst outcome Utility = 0

1-P

Other outcome Utility = P

Utility as a Decision-Making Criterion

- Utility values replace monetary values

Utility

Monetary Outcome

Problem 3
A group of medical professionals is considering the construction of a private clinic. If the medical demand is high, that is, there is a favorable market for clinic, the physicians could realize a net profit of $100,000. If the market is not favorable, they could lose $40,000. Of course they dont have to proceed at all, in which case there is no cost. In the absence of any market data, the best the physicians can guess is that there is 50-50 chance the clinic will be successful. The group has assessed their utility for money: U(-$45,000) = 0, U(-$40,000)=0.1, U(-$5,000)=0.7, U($0)=0.9, U($95,000)=0.99 and U($100,000)=1. a. What would the best decision for the medical professionals using expected utility as the decision criterion? b. Are the medical professionals risk seekers or risk avoiders?

Problem 4
In the past few years, the traffic problems for Lynns hometown have gotten worse. Now, Commonwealth Ave is congested about half the time. The normal travel time to work for Lynn is 30 minutes when Commonwealth Ave is used and there is no congestion. With congestion, however, it takes Lynn 1 hour 20 minutes to get to work. If Lynn decides to take NLEX, it will take 1 hour regardless of the traffic conditions. Lynns utility for travel time is: U(30min)=0.9, U(1 hour)=0.7, U(1 hour 20 min)=0.2. a. Which route will minimize Lynns expected travel time? b. Which route will maximize Lynns utility? c. When it comes to travel time, is Lynn a risk seeker or a risk avoider?