D08: Introduction to R (Online)

This online course covers the basics of programming in R: importing data, performing the necessary data cleaning and transformation steps, creating subsets or merging datasets with other external sources of data. Some of these steps might be a bit different depending on the type of data you intend to work with, but we discuss these differences and show examples of working with all of them. As some participants might have prior experience using other statistical software, we cover how to import and export data to proprietary (STATA, SPSS, etc.) formats. Moreover, we go through applied data analysis and hypothesis testing, such as comparing groups and regression, and mention some AI tools that make writing complex code easier. Topics on data visualization form an inherent part of this course: relying on ggplot2, we’ll create scatterplots, illustrate temporal trends, present distributions in intuitive ways and express regression results concisely with coefficient plots. Following a learning-by-doing approach, course participants will have a chance to solve coding exercises both in teams and alone, and to test their newly acquired knowledge via assignments between sessions.

Introduction to R

Day 1

Why use R? How do you get help when feeling stuck? We’ll cover the basics of R and RStudio, learn what object-oriented programming is all about, perform basic operations, and
review the fundamental data types. The first session will already enable you to import and export datasets, even if they come from proprietary software (STATA, SPSS, etc.). By Monday lunchtime, you’ll also be able to have a glimpse of (potential) relationships between variables by generating a histogram or a scatterplot.

Day 2

As most of the course will rely on packages (collections of useful functions for data wrangling, visualization and more), the session will start with a hands-on guide on how to
install and load them. We will then focus on the skills necessary for data cleaning. The session will cover how to merge and join separate data frames, create subsets, filter out specific observations, delete and create new variables, and remove duplicates.

Day 3

We will cover the fundamentals of working with missing data, dates, and character input. Converting long data frames into wide ones (or the other way around) will help us
restructure our datasets into a form that best suits our analytical purposes. The session will give you the applied skills to perform basic statistical tests and to run some quantitative models. We will compare group means, fit OLS regressions, and learn how to interpret the output R generates for us. In order to make such output submission-ready for journals and dissertations, we will harness the power of stargazer, a package that provides you with neatly formatted tabular outputs from regression models.

Day 4

After this session, course participants will be able to create their first data visualizations with ggplot2. The session demonstrates how to make some of the most
common plots, which can effectively convey underlying patterns, associations, and differences in your data.

Day 5

The remainder of the course is dedicated to the best practices for data visualization. The session covers box plots, violin plots, line charts, visualizations of regression coefficients,
predicted probabilities, and marginal effects. Additionally, examples will illustrate how to modify labels and themes, as well as how to apply different colors, shapes, or types to a particular subset(s) of your data, highlighting subgroup heterogeneity. Lastly, the final day will also introduce some AI tools that can make writing complex code easier, such as chattr (a package allowing you to submit prompts to LLMs directly from RStudio) and GitHub Copilot (that offers autocomplete-style suggestions as you code).

Further readings (none are required, but you might want to consult them before / after the course): 

Kieran Healy: Data visualization. A practical introduction. Princeton University Press

Robert I. Kabacoff: R in Action. Data analysis and graphics with R and Tidyverse. Manning. 

Hadley Wickham, Garrett Grolemund, Mine Cetinkaya–Rundel: R for Data Science. O′Reilly.

This description is subject to change at the discretion of the Instructor

2 Credits

For completion of all work before and during the course, as outlined by the Instructor, and 90% participation and attendance of the course.