Analysis and Interpretation of Social Data (303-0-20)
Instructors
Beth Jane Ortiz Ott Red Bird
As a student, I hated math. Imagine my surprise, when I grew up to be a computational social science professor. It wasn't until I discovered statistics that I started to love numbers. Math is too often taught as though the mysteries of the universe were discovered long ago. In contrast, statistics is one large puzzle, an ever moving and changing enigma with no "right" or "wrong". There is no single way to solve this puzzle - and each method has unique strengths and weaknesses. Thus, the greatest scientists are those with the greatest imagination. This class is not your usual statistics course. Instead of presenting statistics beginning with the math, we begin with the mystery, learning the math along the way - not as the ultimate goal, but as a guidepost for unlocking life's unending hidden questions.
Meeting Info
555 Clark B01: Tues, Thurs 5:00PM - 6:20PM
Overview of class
This course introduces statistics and data analysis for the social sciences, focusing on understanding, interpreting, and deploying data and statistical analysis to understand the social world.
The course begins without numbers, encouraging students to be critical and analytical of the data they encounter every day. Using examples from policy, journalism, and the election, students will practice reading, interpreting, and critiquing empirical analyses.
After gaining familiarity with the reasoning underlying data analysis, the second part of the course will introduce basic statistical analysis. Students will collect, analyze, and interpret data in an area of their interest. The goal is for students to critically engage with statistical topics - to understand the strengths, weaknesses, assumptions, and contributions of statistics to scientific understanding and exploration.
Finally, the course will explore how computation is remaking modern social understanding. Though a focus on machine learning and neural networks, students will explore the contribution of data to human knowledge, while also gaining insight on why such methods pose serious challenges to human well-being.
While not a programming course, students will do exercises and homework using free tools, such as google sheets and the statistical software "R". Labs will be focused on gaining proficiency with these tools.
Learning Objectives
By the end of the course, students should be able to:
• Identity and explain the primary conclusions, assumptions, and scope conditions of analyses used in policy and journalism discussions.
• Articulate the meaning and significance of scientific findings.
• Discuss the validity and accuracy, and challenges therein, of scientific measures.
• Identify the populations, parameters, samples and statistics from a study.
• Critique, evaluate, and re-imagine data plots and figures to effectively convey conclusions.
• Interpret, explain, and articulate the underlying logic of summary statistics, correlations, hypothesis tests, linear regressions, and learning models.
• Conduct analysis of data, including summary statistics, correlations, hypothesis tests, and linear regression using a statistical software.
Teaching Method
Class + Discussion section
Evaluation Method
Weekly assignments and final project
Class Materials (Required)
All materials for this course will be made available on Canvas - no purchase necessary.
Class Attributes
Formal Studies Distro Area
Associated Classes
LAB - 555 Clark B01: Wed 5:00PM - 5:50PM