The analyst was so impressed with your answers to Exercise 5 in Section 3.4 that your advice has been sought regarding the next stage in the data analysis, namely an analysis of the effects of different aspects of a car on its suggested retail price. Data are available for all 234 cars on the following variables: Y = Suggested Retail Price; x1 = Engine size; x2 = Cylinders; x3 = Horse power; x4 = Highway mpg; x5 = Weight x6 = Wheel Base; and x7 = Hybrid, a dummy variable which is 1 for so-called hybrid cars. The first model considered for these data was Y x x x x x x xe =+ + + + + + + + bb b b b b b b 0 11 2 2 33 4 4 55 6 6 7 7 (6.36) Output from model (6.36) and associated plots (Figures 6.53 and 6.54) appear on the following pages . (a) Decide whether (6.36) is a valid model. Give reasons to support your answer. (b) The plot of residuals against fitted values produces a curved pattern. Describe what, if anything can be learned about model (6.36) from this plot. (c) Identify any bad leverage points for model (6.36). The multivariate version of the Box-Cox method was used to transform the predictors, while a log transformation was used for the response variable to improve interpretability. This resulted in the following model