This is a sneak preview of what we and collaborators are developing. The actual open spatial teaching modules on this page will be added throughout 2023.
These open teaching materials are under development at the University of Chicago’s Center for Spatial Data Science, in collaboration with partners. They are designed to teach data science with scientific reasoning, with a specific focus on spatial data and spatial methods. This is generally missing in existing courses.
The materials are developed for three contexts: An undergraduate quarter course, an 8-week high school bridge workshop, and existing courses that seek to add spatial examples with scientific reasoning.
I. One Case, One Undergraduate Course
This is a course to introduce undergraduates to exploratory spatial data analysis in the footsteps of historical figures who were collecting, analyzing and interpreting data to understand how cholera was transmitted – and how it could be stopped. The course is currently being developed by Peter Vinten-Johansen and Julia Koschinsky. It will be tested in spring 2023 at the University of Chicago (quarter system). Below are placeholders for teaching materials related to John Snow, cholera theories, and evidence from 19th century London in the context of spatial data analysis. The materials without active links will be shared in spring 2023.
Peter Vinten-Johansen is Associate Professor Emeritus and an expert of the history cholera in 19th century London. He is the author of Investigating Cholera in Broad Street: A History in Documents (2020) and lead author of Cholera, Chloroform and the Science of Medicine: A Life of John Snow (2003).
Syllabus: Exploratory spatial data analysis with scientific reasoning: Cholera theories and evidence in 19th century Britain, by Julia Koschinsky and Peter Vinten-Johansen (fall 2023).
Instructor Guide: Teaching Scientific Inquiry in the Context of Cholera Theories and Evidence in 19th century Britain by Peter Vinten-Johansen and Julia Koschinsky.
Article: Causality in the Time of Cholera: John Snow & the Process of Scientific Inquiry, by Coleman, Koschinsky & Black (2023).
8 Datasets with Documentation by Falcone, Koschinsky et al. Open data used in this course.
GeoDa Scripts: EDA and ESDA with GeoDa John Snow & the 19th Century Cholera Epidemic by Peter Vinten-Johansen and Julia Koschinsky.
Video & Storymap: How Plausible Is an Explanation? “Experimental” Research Designs to Explain Cholera Transmission by Falcone, Koschinsky & Vinten-Johansen.
XX
II. Two Cases, One High School Workshop
The Data4All High School Bridge Workshop is co-developed by the Data Science Institute (DSI), Argonne National Laboratory (ANL), the Center for Spatial Data Science, and the Office of Civic Engagement. Students learn to program in Python and analyze spatial data with scientific reasoning while solving two case problems (19th century cholera and modern-day covid). Besides programming exercises with small group student mentors, the workshop includes spark activities, small group discussions, lunch speakers, and college preparation resources. High school students from Chicago Public Schools virtually attended the workshop for 1 week in 2021 and in person for 8 Saturdays (for 4 hours) in 2002. The next 8-week workshops will take place in spring & fall 2023 and 2024. The tested teaching materials will be made openly available in late spring 2023.
Data Science Reasoning Framework (spring 2023). Scientific reasoning framework that guides the curriculum and integrates common concepts taught in high school like claim-evidence-reasoning.
Slides (spring 2023) for short lectures on topics like causal explanations, correlation vs. causation, variables about characteristics or mechanisms, quasi-experimental research designs, and space-time patterns.
Instructor Guide (spring 2023). A 100+ page lesson plan for each week developed by John Domyancich (ANL) to train teachers and mentors of the 8-week workshop. Implements the reasoning framework.
10 Jupyter Notebooks with data (spring 2023) by Tyler Skluzacek, John Domyancich (ANL) & Julia Koschinsky (CSDS) to learn data frames & types, variables & lists – with foundational statistics like normalization, correlations, and p-values – and data visualization techniques like scatterplots, histograms, and line graphs.
10 Spark Activities (spring 2023) developed by Bethany Frank (ANL) to learn through games, e.g: asking the right questions, patterns in randomness, spurious correlations, difference-in-difference design, confirmation bias, and competing arguments.
Logistics (spring 2023). A template developed by DSI for initiating and managing the workshop: Student recruitment, onboarding, agendas, checklists, evaluation forms, and more.
XX
III. Many Cases, for Existing Undergraduate Courses
These spatial examples will be modules for flexible integration with existing courses. They are designed to align with four courses / textbooks: 1) Luc Anselin’s Introduction to Spatial Data Science, 2) Fowler & Bueno de Mesquita’s Thinking Clearly with Data (both University of Chicago), 3) Jay Cordes’ Pitfalls, and 4) UC Berkeley’s Sense & Sensibility & Science. Pending funding, spatial cases will also be co-developed to align with curricula at Morehouse College and Howard University.
The Immigrant Paradox in Chicago: Real or Artifact? Exploratory spatial analysis in GeoDa of premature mortality rates in Chicago.
The Original Difference-in-Difference Research Design: John Snow’s Grand Experiment. Illustrated in GeoDa. Also see Thomas Coleman’s R code.
Spatial Analysis of US Presidential Elections. What Happens When you Don’t Have a Hypothesis? by R.E. Stern, Research Assistant at Summer Lab 2020.
Exploring Correlation vs Causation with Experimental Research Designs. A spatialized example of UC Berkeley’s Sense&Sensibility&Science course (spring 2023).
Crime & Temperature: Correlation vs Causation. Will align with Bueno de Mesquita & Fowler’s Thinking Clearly with Data and 9 Pitfalls. (2023)
more examples to come …