Using the least-squares criterion, the researcher obtained the following estimated multiple regression equation: y 1,087 20x3 + 48x4 + 16x5 The coefficient 16 in the estimated multiple regression equation just given is an estimate of the change in average given month (in thousands of dollars) corresponding to a change in rebate amount printer sales in a when of the other independent variables are held constant. If the rebate amount increases by 14 units under this condition, you expect printer sales to increase on average by an estimated amount of