This is an individual/group project, and it will count for 15% of your final grade.  You are expected to work with one or two students in class and submit one project from the group.  Please submit your project on canvas (MS Word document & Excel file) NO LATER THAN 11:59 PM on Friday, August 25th.  Late submission for any reason will lower the grade by 10% each day past the due date and time.  Absolutely no software such as CHATGPT should be used to complete the interpretations. All interpretations MUST be completed in your own words. Note, projects that do not follow this guideline will receive a zero.

Use graphical and descriptive approaches to help UNIQUE’s management understand its customer demographics and to evaluate the promotion involving discount coupons.  Your report has to be double-spaced and typed a minimum of 1,000 words (approximately more than 3 pages) using MS Word.  I will evaluate the quality of your analysis, not quantity. 

The outputs such as tables, graphs, summary statistics produced by using Excel must be attached at the end of your report as appendixes.  Please do not insert any graphs and tables in the MS Word document.  All summary statistics should not have more than 2 decimal places.  All Excel outputs (such as graphs and summary statistics) for each related analysis must be fitted in one sheet and printed in one page.  Hide the data to print each Excel sheet so that the outputs will not be printed too small.  Your project needs to be concise, very organized, and contain the relevant information.  Otherwise, it will significantly affect the grade. 

Given the data table, please make sure to identify the type of each variable before you start analyzing the data.  (For example, determine whether gender is a categorical or quantitative variable.)  At a minimum, your report is expected to include the following and further analysis that helps the management.

1. Write an introduction paragraph to explain the purpose of your data analysis and to identify what you hope to illustrate for Unique’s management.

2. Select one categorical variable. Then, construct a frequency distribution (include relative frequency) for the selected variable by each type of customer (regular/promotional), graph, and describe the characteristics (give a detailed description).  What can you conclude?

 3. To analyze the total number of items purchased, construct an ungrouped frequency distribution, graph, and find the summary statistics (including the quartiles) by each type of customer (regular/promotion).  Label the graphs completely.  Describe the shape of the distribution for each type of customer and discuss similarities or differences by interpreting the graphs and summary statistics.  Discuss the measures of center and variation in detail. What can you conclude?  

 4. To analyze customer age, construct a frequency distribution, graph, and find the summary statistics (including the quartiles) by each type of customer (regular/promotion).  (Think whether you should create an ungrouped or grouped frequency distribution.)  Label the graphs completely.  Describe the shape of the distribution for each type of customer and discuss similarities or differences by interpreting the graphs and summary statistics. Discuss the measures of center and variation in detail. What can you conclude?

 5. Construct a COMPARATIVE (also known as SIDE-BY-SIDE) box-and-whisker plot and find the summary statistics (including the quartiles) for net sales by each type of customer (regular/promotion).  Make sure that you format the x-axes on each plot and compare the plots using the same scale.  Describe the shape of the distribution for each type of customer, and compare the graphs by interpreting the summary statistics, particularly the five- number summary.  What can you conclude?

 6. Develop a scatterplot and explore (discuss) the correlation between customer age and net sales by each type of customer (regular/promotion).  Use the horizontal axis for the customer age to graph.  Find the linear regression line that models the data by each type of customer.  Round the rate of changes (slopes) to two decimal places and interpret them in terms of the relation between the change in age and the change in net sales. What can you conclude?

 7. If all in-store credit card transactions were recorded during the promotion, what would be the mean sales per in-store credit card transaction for each type of customer? Construct and interpret a 95% confidence interval to estimate the amount for each type of customer. Round the upper limit and lower limit to the nearest whole number.

 8. Write a conclusion paragraph to summarize your findings.

 9. Your project needs to be concise, well organized, and contain the relevant information. Your word document must also be double-spaced, free from typos and formatted properly. Your report should contain interpretations with at least four pages in length.

 10. Your report should include appendix/appendices where you should include all excel output. Do not number the questions in your report. Please write in an essay format. DO NOT include your charts/graphs in the essay portion of the report.

  Cover page

  Introduction and objectives

  Statistical analysis and interpretation

  Conclusion

  Appendices (All Excel outputs (charts, graphs, tables, etc.)  must be in the appendix page.

 Students are expected to collaborate with their partners in their group.  However, sharing students’ work in

  Other groups are strictly prohibited.  Unauthorized collaboration is working with students in

  other groups, turning in work which is identical or very similar to other groups’ work or

  excessively relying upon students’ ideas in other groups.  These behaviors violate the LIM College

  academic integrity policy.  It will be reported to LIM College.  LIM College does not tolerate any act of academic

  dishonesty, intentional or unintentional.