Scribd
Upload
182 views24 pages

12 Imperfect Information

The document discusses modeling uncertainty and the expected value of imperfect information. It presents an influence diagram showing the relationship between an economic forecast, market activity, investment decision, and payoff. It also discusses using Bayes' theorem and conditional probability to determine the value of imperfect information, giving an example where a consultant provides information about market demand and activity that is imperfect. The value of this imperfect information can be determined using the probabilities of the consultant's predictions matching the actual outcomes.

Uploaded by

Berthus Yudhistira
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
182 views24 pages

12 Imperfect Information

The document discusses modeling uncertainty and the expected value of imperfect information. It presents an influence diagram showing the relationship between an economic forecast, market activity, investment decision, and payoff. It also discusses using Bayes' theorem and conditional probability to determine the value of imperfect information, giving an example where a consultant provides information about market demand and activity that is imperfect. The value of this imperfect information can be determined using the probabilities of the consultant's predictions matching the actual outcomes.

Uploaded by

Berthus Yudhistira
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 24

Modeling Uncertainty

VALUE OF INFORMATION

Jurusan Teknik Industri

Expected Value of Imperfect Information (EVII)

Jurusan Teknik Industri

Expected Value of Imperfect Information

Jurusan Teknik Industri

Expected Value of Imperfect Information

Jurusan Teknik Industri

Influence diagram for imperfect information in the investors problem

Economy Forecast

Market Activity

Investment Decision

Payoff

Jurusan Teknik Industri

Expected Value of Imperfect Information

Jurusan Teknik Industri

Expected Value of Imperfect Information

Jurusan Teknik Industri

Expected Value of Imperfect Information (EVII)

Jurusan Teknik Industri

Expected Value of Imperfect Information (EVII)

Jurusan Teknik Industri

Expected Value of Imperfect Information (EVII)

10

Jurusan Teknik Industri

Expected Value of Imperfect Information

11

Jurusan Teknik Industri

First step in solving the influence diagram. We reserve the arrow between Economic Forecast and Market Activity

Economy Forecast

Market Activity

Investment Decision

Payoff

12

Jurusan Teknik Industri

Flipping the probability tree to find posterior probabilities required for value-of-information analysis.

What we have

What we need

13

Jurusan Teknik Industri

Bayes Theorem

P(MarketUp EconomistS ays"Up") P(Up "Up")


P(" Up" Up ) P(Up ) P(" Up" Up ) P(Up ) P (" Up" Flat ) P( Flat ) P(" Up" Down) P ( Down)
14

Jurusan Teknik Industri

P ( MarketUp EconomistSays "Up" ) 0.8(0.5) 0.8(0.5) 0.15(0.3) 0.2(0.2)

0.4 0.825 0.485


15

Jurusan Teknik Industri

Expected Value of Imperfect Information

16

Jurusan Teknik Industri

Expected Value of Imperfect Information

17

Jurusan Teknik Industri

Expected Value of Imperfect Information

18

Jurusan Teknik Industri

Expected Value of Imperfect Information

19

Jurusan Teknik Industri

Expected Value of Imperfect Information

20

Jurusan Teknik Industri

Expected Value of Imperfect Information

21

Jurusan Teknik Industri

Expected Value of Imperfect Information

22

Jurusan Teknik Industri

Expected Value of Imperfect Information

23

Jurusan Teknik Industri

Case from perfect information


Imperfect Information In real life problem, perfect information is virtually non existent. Most of the available information is imperfect. To obtain the value of imperfect information we need to apply conditional probability. Consider this example, suppose that the consulting company above offers information that is imperfect. The probability of the consultant said demand would be aggressive if in fact demand will really be aggressive is 0.80. In addition, the probability that the consultant said the market would be poor when in fact it turns out to be poor is 0.90. Determine the value of this information.

24

You might also like