The goal of this course is to introduce students to R for epidemiologic methods. Students will be introduced to base R before moving into the Tidyverse. Each session is a combination of didactic lecture and hands-on practice. Students will clean and analyze actual data sets, learn the importance of data preparation and cleaning, how to visualize descriptive analyses, write their own functions, and run regressions models.

The primary objective of this course is to introduce students to advanced R programming skills so they can (1) more efficiently prepare data for analysis; (2) implement advanced epidemiologic methods in R; and (2) continue learning and problem-solving in R beyond the course. By the end of the course students will be able use R to:

• Enter, read, index, clean, organize, and manipulate (i.e., “wrangle”) epidemiologic data.
• Understand and use packages from the “Tidyverse'
• Understand how to fit linear and generalized linear regression models
• Develop visually attractive graphics based on the grammar of graphics (i.e., ggplot2)
• Write their own R functions for data manipulation and analyses not found in base R.

Some exposure to R is ideal, but not required. Students are expected to be familiar with the file structure of their operating systems (Windows, OS X, or LINUX) and how to download, install, and transfer files. A basic understanding of statistical and epidemiological principles is strongly encouraged but brief introductions to key concepts will be offered as necessary although focus will naturally be on the application and interpretation of statistical and epidemiological concepts in the context of R.

TECHNICAL REQUIREMENTS

Students will need access to a computer with high-speed internet access. In addition, students will need to download and install the following software:

• R, a free multi-platform (Windows, Mac, Linux) user-maintained advanced statistical and scientific computing platform based on the S-plus language. R has versatile and powerful graphics capability. In addition to the thousands of user-contributed packages, the language is easily extendable though simple object-oriented programming. A number of specialized packages will be used e.g., ggplot2, Tidyverse, etc.
• RStudio, a free multi-platform (Windows, Mac, Linux) integrated development environment (IDE) for R designed to make analysis and document production more efficient and reproducible.

None.

Seth Prins, PhD

Click here to download Criminogenic or Criminalized? Testing an Assumption for Expanding Criminogenic Risk Assessment. Prins, S. J. Law and Human Behavior, Online First. 2019. My two programs of research concern the collateral consequences of mass incarceration for public health, and the effects of the social division and structure of labor on mental illness. Two questions have motivated my work to date: First, what are the theoretical and methodological assumptions underlying the growing use of psychiatric categories, such as antisocial personality, to explain and assess the risk of exposure to the criminal justice system, particularly in the context of mass incarceration? Second, what can we learn about the distribution and determinants of mental illness by examining social class as a dynamic relational process, rather than an individual attribute? I am also working on a project to study the role of adolescent substance use as determinant and consequence of the school-to- prison pipeline, disentangling individual risk, social determinants, and group disparities. I explore these questions at the intersections of epidemiology, sociology, and criminology, combining theory-driven analysis with advanced quantitative methods. I am a social and psychiatric epidemiologist interested in pushing the boundaries of the discipline to encompass rich social theory.