Statistical models help us to understand the world. This class explores the use of models for analysis in the social sciences broadly, and in political science specifically. Does a history of slavery in a county influence contemporary political views? Does perceived demographic change impact policy preferences? Does having daughters affect a judge’s rulings? We use the R programming language, RStudio, Git and GitHub. Each student will complete a replication as their final project, an attempt, successful or not, to reproduce the results from a published article in the academic literature. This class provides an introduction to data science and is designed to lay the groundwork for an empirical senior thesis.

Prerequisites: A course on computer programming (Gov 1005, CS 50 or the equivalent), a course on statistics (Gov 1005, Gov 50, Stat 104 or the equivalent) and experience with R and Git. You must have a laptop with R, RStudio and Git installed.

Logistics: Class meets from 12:45 to 2:45 on Wednesdays in S001 Kin-Chung Lam Room, basement of CGIS South. You should be available for work with your classmates on at least one evening prior to class, presumable either Monday or Tuesday.

Course Metaphor