Correct Answer

verified
(a)The decision is whether to share the existing plant in Indiana (with a fixed cost of $2 million)or build a new dedicated plant in Georgia (with a fixed cost of $4 million).This decision is represented in the decision tree by a decision node with two branches.For each decision,there are two outcomes: strong sales (60% probability)or moderate sales (40% probability).This is represented in the decision tree by event nodes with two branches.If the Indiana plant is used and sales are strong,the profit would be (100,000 units)($30,000 - $24,000)= $600 million - $200 million (fixed cost)= $400 million.If the Indiana plant is used and sales are moderate,the profit would be (50,000 units)($30,000 - $16,000)= $700 million - $200 million (fixed cost)= $500 million.If the Georgia plant is used and sales are strong,the profit would be (100,000 units)($30,000 - $20,000)= $1000 million - $400 million (fixed cost)= $600 million.If the Georgia plant is used and sales are moderate,the profit would be (50,000 units)($30,000 - $22,000)= $400 million - $400 million (fixed cost)= $0.The resulting solved decision tree is shown below.The decision to share the plant in Indiana has a higher expected profit of $440 million. 11ea84c6_c8c2_7699_83dc_4b2db6321cb5_TB2462_00 (b)Due to the uncertainty in expected sales for the Vector,GFMC is considering conducting a marketing survey to determine customer attitudes toward the Vector and better predict the likelihood of strong sales.The marketing survey would give one of two results-a positive attitude or a negative attitude toward the design.GFMC has used this marketing survey for other vehicles.For vehicles that eventually had strong sales,the marketing survey indicated positive attitudes toward the design 70% of the time and negative attitudes 30% of the time.For vehicles that eventually had moderate sales,the marketing survey indicated positive attitudes toward the design 20% of the time and negative attitudes 80% of the time.Assuming GFMC conducts such a survey,construct a decision tree to determine how the company should proceed and what the expected annual profit would be (ignoring the cost of the survey).First we must determine an estimate for the probability that the survey will indicate a positive attitude or negative attitude toward the design.Second,given the survey indicates either a positive or negative attitude,we must determine the posterior probability that sales will be either strong or moderate.Both of these calculations can be performed using the template for posterior probabilities provided in the Excel files for Chap.16.These results are shown below. 11ea84c6_c8c2_769a_83dc_4341fb4483d1_TB2462_00 Thus,there is a 50% chance that the survey will indicate a positive attitude and a 50% chance that the survey will indicate a negative attitude toward the new car.Given a positive attitude,the probability of strong sales increases to 84%.Given a negative attitude,the probability of strong sales sinks to 36%.The revised decision tree is shown below.It begins with an event node with two branches for the two possible outcomes of the survey.After the survey results are known,there is a decision of whether to share the plant in Indiana,or open a new plant in Georgia,represented by a pair of branches.Finally,after the decision is made,there will either be strong or moderate sales.This is represented by event nodes with two branches,and uses the posterior probabilities given the results of the survey. 11ea84c6_c8c2_9dab_83dc_3f0ee4e9b575_TB2462_00 If the survey indicates a positive attitude toward the car,they should open a dedicated plant in Georgia.If the survey indicates a negative attitude toward the car,they should share the plant in Indiana.The expected profit is $484 million.(c)The expected value of experimentation is the expected payoff with the information minus the expected payoff without the information.With the survey information,the expected payoff is $484 million.Without the survey information,the expected payoff is $440 million.Thus,the expected value of experimentation in part b is $44 million.This is the most that they should be willing to pay for the marketing survey before it would no longer be worthwhile to conduct.