A company has undertaken a study to predict the calorie content of a serving of breakfast cereal based on protein,fat,fibre,carbohydrates,and sugar content (all in grams).Measurements were taken from 77 different breakfast cereals.A multiple regression model with all five variables was run,resulting in the following output:

= 0.845
-Which measurement is the worst predictor of calorie content,after allowing for the linear effects of the other variables in the model?
A)sugar
B)carbohydrates
C)protein
D)fat
E)fibre

Question

A company has undertaken a study to predict the calorie content of a serving of breakfast cereal based on protein,fat,fibre,carbohydrates,and sugar content (all in grams).Measurements were taken from 77 different breakfast cereals.A multiple regression model with all five variables was run,resulting in the following output:  
  
= 0.845
-Which measurement is the worst predictor of calorie content,after allowing for the linear effects of the other variables in the model?
A)sugar 
B)carbohydrates 
C)protein 
D)fat 
E)fibre

Quizplus · Accepted Answer

The variable with the smallest coefficient in absolute value is the worst predictor when allowing for the other variables in the model. In this case, the coefficient for fibre is -0.008, which is smaller than the coefficients for sugar (-0.074), carbohydrates (0.067), protein (0.040), and fat (0.024). Therefore, fibre is the worst predictor in this model.

A Company Has Undertaken a Study to Predict the Calorie