In this assignment, you are going to take the role of an advisor to the managers at a bank. The bank sells a term deposit product and advertises it using tele-marketing, meaning the bank calls clients to sell the product. In this assignment, your goal is to predict if the client will buy the product and deposit funds with the bank (variable y). This analysis helps to target advertising campaigns better in the future.
1. [20 points] Your first task is to load the call data into Stata, and process them. Make sure you carefully read the description of the data in the readme file. When cleaning and processing the data, make sure that there are no obviously wrong entries and that the variables have the right format (e.g., numeric and dummy variables rather than strings). The variables should be in a format that is usable for regression analysis and work with commands like regress. Potentially helpful commands for this are tabulate, format, destring, mvdecode, and replace. As is common in empirical research provide a table with summary statistics. This gives you and the reader a first impression of the data and provides an opportunity to check for potential problems that might have arisen in the preparation of the data (e.g., data not processed or cleaned properly). For the categorical variable “state”, plot the frequency of each value. Comment on the sample and summary statistics. What is the success rate of the campaign, is the sample balanced, etc… The purpose of this is to give management a first impression of the data and show them that you fully understand the data set.
2. [20 points] Consider the linear probability model:
π¦π = π½0 + π½1 ππππ + π½2 ππ’πππ‘ππππ + π½3 ππππππππ + π½4π ππ₯π + ππ (1)
Estimate the regression model and report the regression output. Interpret the point estimates. According to the model, what is the probability that a female person aged 48 that had a call of average duration with a balance of 250,000€ will buy a deposit product? Comment.
Plot the residuals and test for heteroscedasticity. Report the test results (figure, test-statistics, and p-value). Comment on whether the assumptions of the linear regression model are satisfied. (Hint: Chapter 10.1 of the book could be helpful.)
3. [20 points] Logit model
In this question you are learning about a new model for dependent variables that only take the values 0 or 1. This model is called the logit model. Research how the logit model works and how it can be estimated in Stata (Hint: Start by reading chapter 10.2 of the book.)
Briefly describe the model, highlight the key characteristics and the main differences to the linear probability model. Explain in general how to interpret coefficients of logit models.
Write down the regression equation for the logit model similar to Equation (1) above. Estimate the model and plot the residuals. Compare with your results from Question 2.
Interpret the coefficient estimates. In your answer focus on the economic meaning and implications that management cares about.
4. [20 points] Model design
Note that this question is open-ended: You can do a lot or you can do little. The more you do and the more you show that you understand how to work with data in Stata, the better your score will be on this question.
Extend/adapt the logit model from Question 3 to find the model that best predicts whether a client will buy the product and deposit funds with the bank. Interpret your model and recommend how to target advertising campaigns better in the future.
• Choose variables to include in the model. Think about whether you use variables as they are or whether it could be better to transform variables (e.g., you could use age buckets rather than assume a linear relation with age)
• Analyze goodness of fit statistics, significance of coefficients, residuals, etc..
• You conduct out of sample testing by using only part of the data to develop the model and the remainder of the sample to conduct out of sample testing.
• Think about economic plausibility of your model. Does your model make economic sense? Is it informative about what you are trying to achieve?
• Discuss whether you think some other variables that are currently not included in the data set could play a role? Recommend to update the data collection for next marketing campaign?
• Concisely summarize your findings such that management understands the main takeaway.
CS 340 Milestone One Guidelines and Rubric Overview: For this assignment, you will implement the fundamental operations of create, read, update,
Retail Transaction Programming Project Project Requirements: Develop a program to emulate a purchase transaction at a retail store. This
7COM1028 Secure Systems Programming Referral Coursework: Secure
Create a GUI program that:Accepts the following from a user:Item NameItem QuantityItem PriceAllows the user to create a file to store the sales receip
CS 340 Final Project Guidelines and Rubric Overview The final project will encompass developing a web service using a software stack and impleme
