R for SPSS Users with LLM Applications - A Short Course

This course takes the perspective of the SPSS user. SPSS users know how to carry out their preferred analyses in SPSS. However, in moving to R, analysis approaches, workflows, and output often differ from R defaults. You’ll learn how to produce the statistics commonly used and reported in SPSS using R. Throughout the course, there will be sections highlighting ways to improve workflows with LLM support.

The course is hands-on. There are regular exercises to ensure understanding and online help for those who get stuck. You are encouraged to bring your own data and post questions about translating your SPSS-focused analyses to R.

You’ll become familiar with using R through the RStudio interface while learning how to transition smoothly into the R environment. You will leave with course materials, including detailed examples of all common social science analyses and approaches.

To engage with hands-on exercises, you will need to have a current version of R and RStudio installed on your computer. Both are free and available on all major platforms. Prior to the course, you will receive detailed instructions for installation on Windows and Macintosh platforms.

For LLM support, the instructor will use the most recent paid version of Claude. However, most modern LLMs (e.g., ChatGPT and Gemini) will be useful for understanding, modifying, and interpreting longitudinal models.

If you are an SPSS user who wants to move into the R environment, this course is designed to help you make that transition smoothly and with a minimal learning curve.

If you are looking to transition to R from a different software, check out R for SAS Users or R for Stata Users.

Introduction to the R computing environment

• • Basics of code structure
  • Tour of RStudio setup and features

Importing data

• • Viewing data in RStudio
  • Hands-on work focused on importing data

Introduction to packages

• • Installing packages
  • Useful packages
  • Errors that occur when installing packages and how to fix them

Importing SPSS (and other) files

• • Hands-on work importing an SPSS file and installing and loading packages
  • Overview of strategies for importing other data formats
  • How to point functions to data

Basic data visualizations

• • Histograms
  • Bar charts
  • Scatterplots
  • Boxplots
  • Hands-on work with graphs

Introduction to LLMs

• • Choosing an LLM
  • Building projects
  • Ethical use and increasing efficiency

Data types

• • Review of SPSS data types (scale, ordinal, nominal)
  • Drawing connections between SPSS data types and R data types
  • Common problems and solutions – e.g., factors imported as numbers, factor levels in wrong order

Introduction to data manipulation

• • Review of common SPSS tasks such as select cases, transform-compute, recode, create summary scores
  • Carrying out common SPSS tasks in R
  • Hands-on work with data

Descriptive statistics

• • CT and dispersion
  • Skew, kurtosis
  • Percentiles
  • Frequencies
  • Hands-on work running various descriptive measures

Correlations/simple linear regression

• • Pearson’s correlation approaches
  • Working with scatterplots
  • Linear regression
  • Adding regression lines to scatterplots
  • Hands-on work

LLM approaches to work more efficiently

• • Best practices for LLM queries
  • Setting up LLM projects for better answers
  • Applications for solving various coding problems

Chi-square tests and variations

• • Goodness of fit and test of independence
  • Frequency/proportion tables
  • Effect sizes
  • Hands-on work with chi-square including installing lsr package

ANOVA basics

• • One factor and factorial
  • Descriptives for ANOVA
  • Graphs for ANOVA (introduction to ggplot2)*
  • Setting up R for factorial ANOVA to match SPSS settings*
  • Getting information out of the ANOVA via summary
  • Hands-on work with ANOVA

Multiple regression

• • Basic output
  • Getting additional statistics (e.g., standardized coefficients)*
  • Assumption plots
  • Hands-on work with multiple regression

Using LLMs for advanced coding

• • SPSS syntax to R code
  • Generating code from existing research

Mediation

• • Basics of mediation in R*
  • Using the PROCESS macro for R*
  • Using lavaan to conduct mediation*

Psychometrics

• • Reliability estimates*
  • Exploratory factor analysis*
  • Confirmatory factor analysis*

*Time permitting. However, materials and annotated code for these topics will be provided.

“I had the opportunity to practice writing code during the seminar, which gave me the confidence that I would be able to write, copy, paste, and edit the code on my own after the course. I would say this course was very worthwhile and very valuable in building my repertoire of coding in different statistical packages.”
  Mary Mitchell, Pennsylvania State University

“The course covered everything I would want to know on how to get started and gave me the tools to learn more advanced things on my own. I definitely feel more confident using R now.”
  Cara MacInnis, Acadia University

“I found the content and pacing to be exactly right. I have been meaning to make the switch to R for over five years, and now I finally feel like I have the foundation to continue my own learning.”
  Amy Pace, University of Washington

“I was very impressed with this course. It covered everything needed to start with R. The timing was excellent, and questions were answered very quickly.”
  Phil Petri, Technical University of Braunschweig

“I liked that this course acknowledged the weirdness of some aspects of R and drew attention to how to resolve them. I appreciated that there was an opportunity for a lot of hands-on work. This was the fourth R course I’ve taken, and I think this is the one that has finally gotten things to click for me. The comprehensive slides were fabulous!”
  Sam Garbers, Northeastern University