I mostly teach quantitative methods for social scientists at both the undergraduate and graduate level, and am always interested in improving my teaching to encourage efficient learning and practical application of methods for both consumers and producers in their research. I was a Fellow in the Omicron Cohort in the Madison Teaching and Learning Excellence (MTLE) program at UW-Madison in 2019-2020.
Graduate students interested in prepping for the methods sequence, depending on differences in backgrounds, might find a few of the below options helpful, especially in the summer before starting the program.
Refresh or get familiar with the following subfields of mathematics (for a rough guide of key materials and concepts see the following mathematics review handout I’ve put together). Note textbook editions generally won’t matter throughout.
Calculus. Important aspects are derivatives, integration (optimization). Suggested texts are Stewart Calculus books.
Linear algebra. Important aspect is matrix notation. Suggested texts include Spence et al. “Elementary Linear Algebra” and Golub and Van Loan “Matrix Computations”.
Probability. Important aspects include random variables and expectations of random variables. Suggested texts include Ross' “A First Course in Probability.” For a nice probability cheat sheet you can also check out William Chen’s review.
Download, install, and conduct a few beginner’s exercises in the programming language R, and its more user friendly interface RStudio.
Wickham & Grolemund “R for Data Science”.
Matloff’s “The Art of R Programming”.
Familiarize yourself with LaTeX typesetting. At some point in your grad career it is likely you will encounter or need to write in LaTeX, so early familiarity with this typesetting system can help (resources abound online for this) though I recommend for starters:
Fall 2022, 2023
PS 812: Intro to Statistical Analysis
PS 919: Intro to Machine Learning
Spring 2022
[Harvard] Gov 50: Data
The course introduces basic principles of statistical inference and programming skills necessary for data analysis and is primarily designed for undergraduate students in the social sciences. Students will learn the statistical and computational principles necessary to conduct basic statistical tests and regression analyses of empirical data. Students will be able to do so using the R programming language and present graphs and plots of their results and findings. More specifically, the course covers basic probability, univariate inference, linear regression and its applications in causal inference strategies.
[Harvard] Gov 2018: Introduction to Machine Learning
This course serves as a graduate-level introduction to machine/statistical learning for social scientists. It will cover some, but not all, common techniques to collect, analyze and utilize large and unstructured data for social science questions. The general goal of this course is to introduce students to modern machine learning techniques and provide the skills necessary to apply the methods widely. Note, this course does not utilize Python or Julia. All computation work is conducted in R.
Fall 2020
PS 812: Intro to Statistical Analysis
First graduate course in quantitative methodology in Political Science. No prerequisites required.
Previous syllabi: Fall 2019.
Source: Seeing Theory, Brown University
PS 919: Intro to Machine Learning
This is graduate introduction to the basic principles of machine learning. It focuses heavily on so-called supervised learning where example data is available from which an algorithm can learn before it is applied to solve a problem.
Prerequisites: PS 812, 813 and 818. Familiarity with R is assumed.
Previous syllabi: Spring 2020.
Source: New York Times