Aggregating, Analyzing, and Visualizing Student Survey Data to Improve Targeted Local Support - Module 3
The case uses anonymous socio-economic survey data from middle- and high-school students enrolled in Fe y Alegría schools in Bolivia (FyA:B) to teach data aggregation, data cleaning, and data visualization to undergraduate and/or graduate business school students. The content of the survey data relates to third world educational and economic realities and therefore increases awareness that leads to service for the common good. While anonymous, the survey data provides context on the daily life of disadvantaged communities served by FyA:B schools and can assist Jesuit business schools in aligning with the Inspirational Paradigm by focusing on the plight of the underserved, by providing actionable lessons and assignments, by stimulating critical reflection, and by offering opportunities to engage with FyA:B’s work.
The case covers basic data combination, analysis, and visualization skills and was designed for up to twelve-week course sequence intentionally developed to allow flexibility in breadth and depth of coverage. It focuses on fostering familiarity with commonly used software tools (Excel, Alteryx, and Tableau) to develop data analysis skills that have recently been highly valued in the labor market for current STEM and Business college graduates. The case does so by examining anonymized surveys conducted to better understand student socio-economic conditions in FyA:B school communities across different regions over a period of several years. The surveys had either 22 and 28 questions and asked questions regarding students’ access to basic needs (e.g., water, meals) as well as social environment (e.g., living conditions, parent education and occupation). The original objective of the surveys was to help FyA:B schools identify students in most need so targeted tailored support could be made available to them. The case is composed of three modules that can be used in their entirety or only in part, so at the instructor’s discretion it is possible to teach the material in less time (either by eliminating content or by compressing delivery).
Module 3: The third module is composed of three parts and can be taught in four to six weeks depending on the desired level of immersion and reflection.
Module 3 Part 1: Data union across multiple collection periods (data preparation) Part 1 covers data preparation extending the one-year aggregation for multiple schools to multi-year aggregation. Module 3 Part 1 should be taught in one week.
Module 3 Part 2: Initial understanding of cleaning through imputation (data cleaning) Part 2 covers data cleaning with a special focus on data imputation either through statistical methods, use of a flag, or application of multi-question logic. Module 3 Part 2 can be taught in one to two weeks depending on the desired level of immersion and reflection.
Module 3 Part 3: Analysis and storytelling using Excel pivot tables and advanced Tableau graphics (data visualization) Part 3 covers data visualization and articulation of the story told by the data. It builds on Excel data visualization capabilities such as pivot tables and pivot charts and introduces the more powerful capabilities of Tableau. Besides creating higher level dashboards using Tableau, Module 3 Part 3 has the explicit objective of encouraging students to use the UN SDGs to explore the various dimensions of social exclusion expressed in the data, intentionally leading them to reflect on the implications of the raw data and to connect that data to the lived reality in Bolivia. Module 3 Part 3 can be taught in two to four weeks depending on the desired level of immersion and reflection.