Advanced Statistics in Political Science. POL 518/618 at the University of Miami. 2020 Syllabus.
This class teaches students advanced mathematical and computational methods for analyzing quantitative social science data. The course covers data cleaning, multiple regression with continuous and binary variables, and basic statistical coding, as well as writing and publishing in political science. Class time will include statistical lectures as well as hands-on data labs and coding exercises. Students will develop a group final project where they answer a social science question with a statistical analysis and interpret the analysis in a publishable social science paper. Special topics lectures will depend on the needs of student research projects and can include time series, machine learning, or panel data. The course uses the open source R software.
Social Movements. POL 362 at the University of Miami. 2020 Syllabus.
From the civil rights movement in the U.S. to the indigenous movements in Bolivia, social movements can bring lasting political change to countries. In this course, we will address questions central to social movement activists and researchers: How does a social movement start? Why do some campaigns become social movements while others do not? What sustains a social movement? Why do some social movements reach their goals while others do not? The course will draw on examples from across the Americas and on current social movement research. Students will develop a final project or research paper for a final grade.
Activism. POL 598 at the University of Miami. 2018 Syllabus.
How can individuals affect change in political systems? What tactics and strategies mobilize others? When and how is activism effective? This course explores what activism is, the history and development of activism around the world, and which activist strategies work best. Students will learn about the social science research and theory on activism and how to be effective activists. The course covers theory and research in lectures and academic readings. Assignments will send students into the city to participate in local politics, work with local organizations, and try activist strategies themselves. Students will work together on a final activism project in the community.
Introduction to Machine Learning for Social Scientists. Government Department Methods Workshop on April 19th, 2017. University of Texas at Austin. Slides (contact me for example code and data).
Machine learning is an increasingly common tool for data analysis. In this short course, we cover the basics of machine learning: what it is, why and how social scientists can use this family of methods, and what fits under the machine learning umbrella. We go through examples in R of decision trees and random forest classifiers. The course also covers useful techniques that can be integrated into any analysis, particularly parallelization and cross-validation. The course closes with a discussion of extensions to unsupervised learning, implementation in Python, and causal inference with machine learning, and suggests resources for students to continue learning on their own time.
Creating a Professional Website. Graduate Student Workshop on August 23rd, 2016. University of Texas at Austin. Slides.
Personal, professional websites describe your research interests, ongoing work, and accomplishments in a central location. Personal pages are most important for when prospective employers look you up online, but can also be useful for conferences, networking, and disseminating your research. This workshop compares different platforms and provides templates to get you started. We cover topics like how to SEO your page so it actually shows up when people Google you, why you should spend the $100 to host it in your name instead of getting a free site (and how to do that), and adding Google Analytics.
Resources (these are the free online tools that I have used in my own work and recommend to others)
Should You Go To Grad School? (pocket lecture that I give to my students)
Job Market Guide (written by UT political science job candidates in 2017)
Making your own website:
Machine Learning for Political Scientists:
- Computational Legal Studies (includes course slides and tutorials for starting from a social science background).
- Intro to Machine Learning course from Udacity.
- Muchlinski, D., Siroky, D., He, J., & Kocher, M. (2016). Comparing random forest with logistic regression for predicting class-imbalanced civil war onset data. Political Analysis, 24(1), 87-103. Link to article.