Statistical computing is a quickly changing field. Standard techniques of today would have been difficult to execute fifteen years ago and impossible in the early 1990s. Rapid improvements i computing power have been accompanied by swift changes in standard statistical methods. In just the last decade, techniques ranging from Markov chain Monte Carlo (MCMC) simulation, randomization inference, network analysis, and non-parametric matching have moved from being novel, advanced applications to commonplace across the social sciences.
This class is designed to achieve two broad objectives. More narrowly, it aims to guide students as they learn the specifics of the R programming language, a powerful statistical computing environment widely used in the fields of political science, network analysis, machine learning, and statistics. Achieving this goal will require students to learn commands, best practices, and work-arounds specific to the sometimes idiosyncratic R language.