3.2 LEAST-SQUARES REGRESSION PREDICTING WITH REGRESSION LINES Mathematical equations that are used to model data shown in scatterplots are call regression equations (or regression lines). The scatterplot shows the mileage (1000 miles) and price (in dollars) for 18 Ford F-150 pickup trucks. The regression equation is # ???? 1. = 40770 173.6????. Rewrite the equation using descriptive variable names. 2. You want to buy an F-150 that has been driven 39000 miles. Use the regression equation to predict the price. 3. The owner used the truck while you were deciding whether to buy it, so now it has been driven an additional 1000 miles. What is the predicted price now? 4. Calculate the difference in the two predicted prices. Does this number look familiar? 5. Identify and interpret the slope of the least-squares regression line. 6. Predict the price of a used F-150 that has been driven 0 miles. 7. Explain why it is not reasonable to make the prediction above. (Hint: look at the scatterplot.) 8. Identify and interpret the y intercept. 9. Look at your previous prediction for an F-150 that has been driven 39000 miles. An F-150 that was driven 39000 miles is advertised for $31000. Is this more or less than predicted? By how much? (This value is the residual, or prediction error.) THE CONCEPT O