To answer Questions 6-9, you may have to build your own regression models. Please do not include interaction variables (slope-dummies or other variables created by multiplying two or more variables). Remember to check the soundness of your specifications (linearity and homoskedasticity). Use a significance level of at least 20 percent when deciding to drop variable(s). 6. Develop a sound regression model to estimate and predict the winning bid (Price) on the final contract for the year, which has the following characteristics: The estimated cost is $1,000,000, of which $700,000 is due to fixed costs, and the four contractors interested in the project are expected not to rig the auction. (a) Write down the estimated regression equation and explain how you came to choose it. (b) Give a point estimate for the winning bid and provide an interval that will contain the winning bid with 90 percent confidence. (c) How confident are you that in this project the winning bid will come in under budget (so that Johnson will earn his bonus)? 7. Johnson wants to be at least 75 percent sure that he will earn his bonus. He knows that contractors rely considerably on ODOT cost estimates. He has suggested to you that he advertise ODOT's lower-range cost estimate (i.e., 15 percent less than he would normally advertise) for this project only (i.e., the project described in question 6), and reduce all the component costs (i.e., FairPy and FxCost) in line with this reduction. He is sure that contractors would treat this as a 15 percent cheaper project and adds, "Nowhere does it say that our estimate should split the range-anywhere in the range could be our 'best estimate."" (a) How likely is it that Johnson will earn his bonus under this course of action? Will he be satisfied? (b) Will you be satisfied? What should you say to Johnson? What course of action should you take? Are there arguments you could make to him or his superiors that hold apart from ethical considerations? Questions 8 and 9 are not concerned with Bob Johnson. Rather, they ask you to address topics of frequent relevance to ODOT 8. It often happens that just before putting a job up for auction, ODOT realizes that the project requirements have changed. For example, ODOT may learn that one more pedestrian bridge is needed than originally planned. For a common type of project it is known that an additional bridge does not affect job duration or road length but that it will increase fixed costs (FxCost) by 15 percent and overall estimated costs (FairPy) by 5 percent. Your goal is to estimate the percentage increase in the winning bid (the Price of the contract) that will ultimately result from the change in projected costs in such projects. (a) What regression would you use to estimate the increase in Price? Write down the estimated regression equation and explain how you arrived at that regression. (b) Using this regression, what is your estimate for the percentage increase in the Price of this contract