Presentation is loading. Please wait.

Presentation is loading. Please wait.

Session 6b. Decision Models -- Prof. Juran2 Overview Decision Analysis Uncertain Future Events Perfect Information Partial Information –The Return of.

Similar presentations


Presentation on theme: "Session 6b. Decision Models -- Prof. Juran2 Overview Decision Analysis Uncertain Future Events Perfect Information Partial Information –The Return of."— Presentation transcript:

1 Session 6b

2 Decision Models -- Prof. Juran2 Overview Decision Analysis Uncertain Future Events Perfect Information Partial Information –The Return of Rev. Thomas Bayes

3 Decision Models -- Prof. Juran3

4 4

5 5

6 6

7 7 Ctrl + Shift + T to modify a selected node

8 Decision Models -- Prof. Juran8

9 9

10 10 Type in probabilities in the cells above “outcome” labels

11 Decision Models -- Prof. Juran11 Type in payoffs in the cells below “outcome” labels, and ONLY below outcome labels

12 Decision Models -- Prof. Juran12

13 Decision Models -- Prof. Juran13 TreePlan Jargon Outcomes(states of nature) Event Node(a.k.a. chance or probability node; tree splits into multiple outcomes) Decision Node(a.k.a. choice node; tree splits into multiple decision alternatives) Terminal Node(the end of a branch; a specific combination of decisions and events) TreePlan-185-Guide.pdf(pretty good documentation) Ctrl+Shift+T(context-specific TreePlan menu)

14 Decision Models -- Prof. Juran14 TreePlan Issues Limited to 5 branches from any node Runs slowly; Freezes frequently Graphics don’t appear until you click near them Copy and Paste Subtree doesn’t always work Copy from Event Nodes only? Paste grayed out? Clipboard error messages When Paste Subtree does work, can take a LONG time

15 Decision Models -- Prof. Juran15 Example 2: TV Production Witkowski TV Productions is considering a pilot for a comedy series for a major television network. The network may reject the pilot and the series, or it may purchase the program for one or two years. Witkowski may decide to produce the pilot or transfer the rights for the series to a competitor for $100,000.

16 Decision Models -- Prof. Juran16 Witkowski’s profits are summarized in the following profit ($1000s) payoff table: If the probability estimates for the states of nature are P (Reject) = 0.20, P (1 Year) = 0.30, and P (2 Years) = 0.50, what should Witkowski do?

17 Decision Models -- Prof. Juran17

18 Decision Models -- Prof. Juran18 Value of Perfect Information

19 Decision Models -- Prof. Juran19 Perfect information (if it were available) would be worth up to 125 - 100 = 25 thousand dollars to Witkowski. This is referred to as expected value of perfect information.

20 Decision Models -- Prof. Juran20 For a consulting fee of $2,500, the O’Donnell agency will review the plans for the comedy series and indicate the overall chance of a favorable network reaction.

21 Decision Models -- Prof. Juran21

22 Decision Models -- Prof. Juran22

23 Decision Models -- Prof. Juran23

24 Decision Models -- Prof. Juran24

25 Decision Models -- Prof. Juran25 What should Witkowski’s strategy be? What is the expected value of this strategy? The best thing to do is to forget about O’Donnell and sell the rights for $100,000.

26 Decision Models -- Prof. Juran26 What is the expected value of the O’Donnell agency’s sample information? Is the information worth the $2,500 fee? What is the efficiency of O’Donnell’s sample information?

27 Decision Models -- Prof. Juran27

28 Decision Models -- Prof. Juran28

29 Decision Models -- Prof. Juran29 Decision Alternative Expected Value Produce Pilot 99.65  Optimal Favorable O’Donnell Report Sell to Competitor 97.50 Produce Pilot -4.20 Unfavorable O’Donnell Report Sell to Competitor 97.50  Optimal The overall expected value with sample information ( EVwSI ) is:  2211 IPIEVIPI   98. 31.0*5.9769.0*65.99  (Note that we are assuming here that we will always adopt the optimal strategy in light of whatever information O’Donnell provides.)

30 Decision Models -- Prof. Juran30

31 Decision Models -- Prof. Juran31 Expected Value of Sample Information

32 Decision Models -- Prof. Juran32 What is the expected value of the O’Donnell agency’s sample information? Is the information worth the $2,500 fee? If we pay O’Donnell the $2,500 fee, our overall expected value drops by $1,020. This implies that the O’Donnell report is worth We would be willing to pay up to (but no more than) $1,480 for the O’Donnell report. (This is one way to address the question, “How much should Witkowski be prepared to pay for the research study?”)

33 Decision Models -- Prof. Juran33 Efficiency of Sample Information The efficiency of sample information is calculated using this formula: In other words, the market research project gives us information with less than 6% of the utility of having perfect information.

34 Decision Models -- Prof. Juran34 Conclusions Don’t buy the O’Donnell report Sell the script to the competitor Earn $100,000

35 Decision Models -- Prof. Juran35 Summary Decision Analysis Uncertain Future Events Perfect Information Partial Information –The Return of Rev. Thomas Bayes


Download ppt "Session 6b. Decision Models -- Prof. Juran2 Overview Decision Analysis Uncertain Future Events Perfect Information Partial Information –The Return of."

Similar presentations


Ads by Google