CSS 211 Syllabus
Course Overview
This course is an introduction to statistical methods and computational tools for computational social science (CSS) research. Students will develop proficiency in R programming while learning foundational concepts for working with CSS data, including: data wrangling and visualization, regression, and model selection. The course emphasizes hands-on application of techniques to real-world datasets, as well as discussion of ongoing methodological and epistemological issues in the study of human behavior.
Learning Outcomes
My goal is that by the end of this course, students will be able to:
- Define and explain key concepts in statistical inference and regression analysis.
- Identify appropriate visualizations and statistical methods for different kinds of research questions and datasets.
- Implement data wrangling, visualization, and analysis workflows in R.
- Interpret and evaluate results (visualizations, fit models, etc.) in the context of a research question.
- Design and implement a complete statistical analysis project from research question to interpretation.
Teaching Team
| Name | Role | OH Time | |
|---|---|---|---|
| Sean Trott | Instructor | Friday 1-2pm (CSB 259) | sttrott@ucsd.edu |
| Xiaohan Wu | TA | Monday 11am-12pm (SSB 104) | xiw021@ucsd.edu |
Prerequisites
Students should have a basic understanding of probability theory and statistics; some experience with a programming language (e.g., Python or R) is encouraged but not required.
Grading and Assessments
| Assessment | Percentage |
|---|---|
| Labs | 20% |
| Concept quizzes | 20% |
| Midterm | 25% |
| Final project | 35% |
Labs (20% total): 4 coding labs, completed in R and submitted via Canvas. Students may collaborate on labs with each other and seek help from their TA/instructor.
Concept quizzes (20%): 4 short quizzes, held over Canvas, designed to test and improve conceptual intuitions about course topics.
Midterm (25%): A paper midterm held in-class testing knowledge of course material.
Final project (35%): A rigorous replication (and possible extension) of existing empirical work (published or otherwise) in a student’s discipline of interest. Final projects should be completed independently; students will turn in both a written report and present their work in a short in-class presentation the final week of class. (A rubric will be provided separately.)
Rounding
My course policy is not to round up grades for two reasons:
- If rounding is applied selectively (i.e., only to students who ask), it is unfair to other students.
- If rounding is applied across the board, it simply redefines the boundary between two letter grades (e.g., making an 89% the cut-off for an A-).
Using AI
Tools like ChatGPT can be incredibly helpful for learning to code (or speeding up the process). At the same time, I think it’s crucial to learn the foundational skills and concepts that will allow you to use these tools to their full potential. That is the main motivation for having an in-class midterm: ultimately, I cannot force anyone to complete homework on their own without using ChatGPT (or equivalent tools), and I wouldn’t even claim that people shouldn’t consult ChatGPT for additional help or questions; but in order to perform well on the midterm, you will still need to learn the concepts.