13.4 AN APPLICATION OF LOGISTIC REGRESSION MODELING
Let us revisit the clothing_sales_training and clothing_sales_test data sets. This time, our goal is to determine whether or not customers have a store credit card, so our marketing team can send out advertisements to non‐holders, enticing them to sign up for a card. Our response variable in this case is binary: Yes, the customer has a card; or No, the customer does not. Since the response variable is binary, we will use logistic regression.
Our provisional logistic regression model will be
![equation](https://static.packt-cdn.com/products/9781119526810/graphics/images/c13-disp-0009.png)
The results of the regression of Credit Card on the two predictor variables are shown in Figure 13.1. The p‐values shown in the output tell us that both variables belong in the model. When we cross‐validate the results with the test data set, we obtain the results shown in Figure 13.2.
![No alt text required.](https://static.packt-cdn.com/products/9781119526810/graphics/images/c13f001.gif)