A sample of 20 automobiles was taken, and the miles per gallon, MPG, horsepower, and total weight were recorded.

You may assume X1 = hrsepwr, and X2 = weight. You may also define using different variable names but be consistent.

Required:

a) Develop a linear regression model to predict MPG, using horsepower as the only independent variable. Develop another model with weight as the independent variable. Which of the two models is better? Why? Make sure you appropriately label all Excel outputs.

b) Using the same data given, develop multiple regression model. How does this compare with each of the models in (a)? Just all the relevant information to support your responses.

c) Additionally:

i. Use just the multiple regression model you developed in (b) to predict MPG if HrsPwr is set at 150 and Weight is 4400.

ii. Next use the regression models for HrsPwr and Weight separately (independently) for HrsPwr= 150 and Weight= 4400 and predict MPG.

iii. Based on you analyses above c (i & ii), and information gathered from a & b, which forecast do you think would be more accurate/realistic and why?

\begin{tabular}{rrr} mpg & \multicolumn{1}{l}{ hrsepwr } & weight \\ 44 & 67 & 1844 \\ 44 & 50 & 1998 \\ 40 & 62 & 1752 \\ 37 & 69 & 1980 \\ 37 & 66 & 1797 \\ 34 & 63 & 2199 \\ 35 & 90 & 2404 \\ 32 & 99 & 2611 \\ 30 & 63 & 3236 \\ 28 & 91 & 2606 \\ 26 & 94 & 2580 \\ 26 & 88 & 2507 \\ 25 & 124 & 2922 \\ 22 & 97 & 2434 \\ 20 & 114 & 3428 \\ 21 & 102 & 2812 \\ 18 & 114 & 3382 \\ 18 & 142 & 3197 \\ 16 & 153 & 4380 \\ 16 & 139 & 4036 \end{tabular}