BK's nutrition sheet lists many variables. Here's a multiple regression to predict calories for Burger King Foods from Protein content (g), Total Fat (g), Carbohydrate (g), and Sodium (mg) per serving:

a) Do you think this model would do a good job of predicting calories for a new BK menu item? Why or why not?
b) The mean of Calories is 453.98 with a standard deviation of 234.63. Discuss what the value of 5 in the regression means about how well the model fits the data.
c) Does the R2 value of mean that the residuals are all almost equal to zero?

Transcribed Image Text:

Dependent variable is: Calories R-squared-99.88% R-squared (adjusted) 99.88% s 8.178 with 122-5 117 degrees of freedom Source Sum of Squares dF Mean Square F-ratio Regression 6652972.7 Residual 4 1663243.2 24861.63 66.9 7824.2 117 Variable Coefficient SE(Coeff) t-ratio P-value Intercept 0.27812 1.79532 0.15492 0.87715 Protein 3.71339 0.09533 38.95356 <0.0001 Fat Carbs Sodium 0.00879 0.00201 4.37341 <0.0001 9.13441 0.08212 111.23529 <0.0001 3.82954 0.04400 87.03665 <0.0001