Assignment 4: BookBinders: Predicting Response w/ Logistic Regression
Eduardo Citwar, Devon Gould, Vanessa Renteria, Malik Stevenson, Shubh Agarwal
Part I: Logistic Regression
1. Estimate a logistic regression model using “buyer” as the dependent variable
and the following as predictor variables: last total_ gender child youth cook
do_it refernce art geog
2. Summarise and interpret the results. Which variables are statistically
significant? Which seem to be economically important? Interpret the oddsratios for each of the predictors.
 last: 0.9096 - One unit increase in one month since the most recent purchase
decreases the odds of purchasing “The Art History of Florence” by 9.1%.
 total_: 1.001 - One unit increase in the total dollars spent increase the odds of
purchasing “The Art History of Florence” by 0.1%.
 female: 0.4673 - If the customer is female rather than male, the odds of
purchasing “The Art History of Florence” decreases by 53.3%.
 child: 0.8301 - If the customer purchases a children’s book, the odds of
purchasing “The Art History of Florence” decrease by 17%