Pre-Regression Modeling Strategies Workshop

Introduction to R, RStudio, Regression, and the R rms Package

 

The May 2024 course video will be available in early June at which time this page will be updated. The next course is planned for Monday May 13, 2024.

Registration

Even though the 4-day RMS course will not require you to use R interactively, those participants who wish to learn more about R or attain the regression knowledge prerequisite for the 4-day course may wish to take this optional one-day Pre-RMS workshop to enhance R and RStudio) skills, learn about multiple linear regression (a prerequisite for the 4-day course), and to get an introduction to the R rms package that will be used throughout the 4-day course.

The Pre-RMS course is given by Frank Harrell and moderated by Drew Levy.

Target Audience

• Statisticians, epidemiologists, data scientists, and others engaged in analysis of quantitative data who want to learn some R programming and report writing skills using RStudio
• Those with some exposure to statistics but who don’t have the general regression skills needed to fully benefit from the 4-day course and who are seeking to learn about simple linear and multiple linear regression models and regression notation
• Those who want to get an introduction to a complete R Workflow for efficiently analyzing data in a reproducible fashion, using Quarto for creating html reports

Prerequisites

• General knowledge of algebra and statistics, which can also be acquired by studying Chapters 2-8 of Biostatistics for Biomedical Research before the workshop
• Those not using R previously may want to read Chapter 1 of BBR

Detailed Course Topics

• Scope of R and how to set it up
• Introduction to RStudio
• R basics
• Learning R from scripts
• Brief introduction to report construction using Quarto
• File import, annotating data, and analysis file creation
• Survey of R Workflow
• Simple linear regression
• Multiple linear regression
• Regression Modeling Strategies Introduction
  • Section 1.2: examples of use of predictive multivariable modeling
  • Section 1.4: planning for modeling
  • Section 2.1: notation
  • Section 2.2: model formulations
  • Section 2.3: interpreting model parameters
    • 2.3.1: nominal predictors
    • 2.3.2: interactions
    • 2.3.3: inference for a simple model
    • 2.3.4: composite (chunk) tests
• Regression in R: the statistical formula language and fit objects
• R rms package: fitting, diagnosing, plotting to understand the model, general point estimates, getting predictions, chunk tests (ANOVA)
• Linear model case study: Estimating body fat

---

This course is not under the auspices of Vanderbilt University.