Introduction

Welcome to the landing page for the R for Health Data Science or R4HDS seminar series, organized be Health Data Nova Scotia (HDNS). Throughout this course we will be exploring how R can be used within Epidemiology and more generally in health research, with a focus on usage within the analysis of secondary data.

All course content is listed above, and the accompanying lectures are available on YouTube (playlist is here). Note that each class will have breakout sessions that are not recorded, so even with the recordings you will be missing some content if you miss the classes.

Each session will be a roughly 50/50 mix of lecture/programming demo, followed by small breakout groups. I'm looking at a number of different ways to offer the course.

The 4 day structure (180 minutes per class) will be as follows

1. Session 1
   • Basics of R (60 minutes)
   • Data manipulation (60 minutes)
   • Tidyverse and Pipes (60 minutes)
2. Session 2
   • ggplot and modern graphics (90 minutes)
   • Basic Analysis (90 minutes)
3. Session 3
   • Functional reporting (90 minutes)
   • Advanced Analysis (90 minutes)
4. Advanced Analysis
   • Survival and LME (60 minutes)
   • Interactions in Regression Models (60 minutes)
   • Markov Models (60 minutes)

The 10 class structure (90 minutes per class) will roughly follow the following schedule:

1. Intro to R
2. Data manipulation
3. Graphics
4. Biostats 1 (hypothesis tests and regression)
5. Reporting
6. Tidyverse - dplyr
7. Tidyverse - ggplot2
8. Biostats 2 - survival and mixed effects
9. Biostats 3 - gee*
10. Classification Trees