Red or Blue - Campaign organizers for both the Republican and Democratic parties are interested in identifying individual undecided voters who would consider voting for their party in an upcoming election. The Excel file RedOrBlue contains data on a sample of voter with tracked variables, including whether or not they are undecided regarding their candidate preference, age, whether they own a home, gender, marital status, household size, income, years of education, and whether they attend church. Assume a cutoff of 0.5. You are welcome to use either StatTools or SPSS. Classify the data using logistic regression (LR), discriminant analysis (DA), and neural network (NN).

I have already created dummy variables and also divided the database into training and validation (see column J, i.e. 'Partition') sets in the ratio 60:40. Then apply LR, DA, and NN to your training set. Determine the efficacy of your models using the validation set. Specifically, you will compute the metrics shown in the table below (See formulas in Appendix).

1. Present your results in the following format. [15 Points]

Metric	Logistic	Discriminant	Neural Net
Training	Validation	Training	Validation	Training	Validation
Accuracy (#correct)
Overall Accuracy
Overall Error Rate
Specificity
Sensitivity (Recall)
Precision
F1 score

1. In your logistic regression model, increases in which variables increase the chance of a voter being undecided? Increases in which variables decrease the chance of a voter being undecided? [10 Points]
2. Consider a 50-year-old man who attends church, has 15 years of education, owns a home, is married, lives in a household of four people, and has an annual income of $150,000. Use your logistic regression model to classify this voter - decided or undecided? [10 Points]