Question:

In this assignment, imagine that you work for a company as a data mining expert. You are given a dataset called Default.csv

https://drive.google.com/file/d/14mUU96D6nYxiDDRbe7VpNv57GysYHuuY/view?usp=sharing

and the company requests that you analyze the data using classification. To this end, you will be using logistic regression analysis. Logistic regression has been one of the most popular binary classifiers that has been used in practice. Complete the following tasks using SAS Studio:

Provide the summary statistic as well as histograms for the variables balance and income for the whole dataset. Explain some of the key characteristics of the dataset.

Using conditional statements on the variables default and student, provide the summary statistics (as well as histograms) for the variables balance and income for the different combinations of groups. That is, (1) default = Yes and student = Yes; (2) default = Yes, student = No; (3) default = No, student = Yes; and (4) default = No, student =No. Explain some of the key characteristics of the dataset.

Using the variable default as the response variable, fit a logistic regression model with the predictor variables student, balance, and income. Comment on the output. What can you say about the significance of the predictor variables? How good is the model fit?

Let's assume a credit card applicant is a student with a balance of $621 and an income of $1850. How likely will he/she default according to the fitted logistic regression model? Explain and show calculations.

6.7 (Reachability matrix for reachable canonical form) Consider a system in reach- able canonical form. Show that the inverse of the reachability matrix is given by al a2 an 0 1 a1 . . an-1 = 0 0 1 . . a1 0 0 0 . . . 6.7 (Reachability matrix for reachable canonical form) Consider a system in reach- able canonical form. Show that the inverse of the reachability matrix is given by a a2 an 0 1 a1 . . an-1 W = 0 0 1 . . a1 0 0 0 . . .8-1 Given the following system transfer function Y(s) s + 3 = U(s) $ 2 + 35 + 2 (a) Show its controllability canonical form (b) Show its diagonal controllability canonical form (c) Show its observability canonical formCasey has trained a full regression tree on 304 observations and then used the validation set to prune the tree to obtain a best-pruned tree. The best-pruned tree (as applied to the 202 observations in the validation set) is: SnapPercent 90.28 106 96 SnapPercent SnapPercent 85.09 95.37 53 53 71 25 Awards Awards 14.73 20.71 6.75 7.25 48 23 11 14 GamesMissed GamesMissed 1.5 32.52 2.5 46.73 0 48 0 11 50 23.61 47.83 32.744 pts Question 7 If you know the values of a quantitative Y and five quantitative X's, then in an attempt to predict Y you can use if you have a linear model and if you do not. Repression Trees Logistic Regression Regression Neural Networks Exponential Smoothing Moving Averages Classification Trees Regression Trees 4nts