While the previous information is interesting, there are some limitations in its use. The winners of the 17 other awards are known only a few minutes before the Best Picture award is announced. Instead of using other Academy Awards to predict the probability of Best Picture, it may be more useful to use other award ceremonies to predict the likelihood of winning Best Picture. Hannah, Allie, and Phillip also collected the following data:
Number of Golden Globe nominations
Number of Golden Globe wins
Number of Screen Actors Guild (SAG) nominations
Number of SAG wins
a. Create a logistic regression model using all four explanatory variables. Which variables appear to be most significant?
b. Using only the Oscars2 data set, submit the model with the fewest number of terms that best estimates the probability of winning the Best Picture award.
c. Compare your model in Part B of Exercise 11 to the one from Part B above. Explain which model is better.
d. Combine the Oscars and Oscars2 data sets to include a total of 21 explanatory variables. Create the model with only a few variables that best estimates the probability of winning the Best Picture award. Is this new model better than the one created in Part B of Exercise 11?