R for SAS Users - A Short Course

The first day of the course will begin by immediately getting you comfortable with the computing environment, writing R code, and working with datasets and variables. We will cover data manipulation and wrangling issues, which will introduce you to the tidyverse suite of R packages. Day 1 will also get you started with the ggplot2 package, which applies the “grammar of graphics” principles for data visualization.

The second day of the course will cover additional data merging procedures, including column-wise inner, outer, left and right-joins, and row-wise dataset concatenation. We will also cover statistical hypothesis tests and modeling approaches (ANOVA, linear and logistic regression). Along with these methods, R packages will be covered which are helpful for manipulating model output objects for interpretation and visualization. Time permitting, Day 2 will end with a brief introduction to creating “reproducible reports” using R Markdown and Quarto.

The course will intersperse lecture with slides with hands-on active learning modules. You are encouraged to write code and work through the examples in class with immediate help from the instructor. Take-home exercises will be provided at the end of each day for you to try on your own. We will review the Day 1 take-home exercises at the beginning of Day 2 and the Day 2 take-home “answer key” code will be provided.

To engage with hands-on exercises, you will need to have a current version of R and RStudio IDE (integrated development environment) installed on your computer. Both are free and available on all major platforms.

This course is for SAS users who want to transition to the R programming and computing environment. It is designed for attendees who want to transition to R with a minimal learning curve.

Day 1

• Understanding what is similar and different between R and SAS (understanding R packages).
• The RStudio development environment – organizing your analysis project: code, data, output, and other files.
• Importing and exporting data.
• Working with datasets, variables, and other “objects”.
• Getting started with executing code at the command line and writing longer scripts and programs.
• Data wrangling (introduction to the tidyverse and dplyr and tidyr) – part 1 (filtering, selecting, sorting, pivoting, descriptive statistics and summaries).
• Data visualization (introduction to ggplot2).

Day 2

• Data wrangling – part 2 (merging datasets by row or column, performing joins).
• Statistical tests (t-tests, chi-square and related non-parametric tests) – understanding and manipulating output objects.
• Introduction to linear models (linear and logistic regression and ANOVA).
• Helpful R packages for improving, interpreting, and visualizing model output.

Time permitting

• Pulling it all together – brief introduction to R Markdown and Quarto (writing reproducible reports).