Exploring and predicting using linear regression in R
This workshop is designed to increase participants understanding of statistical relationships between data. It introduces principles and methods of regression models using R, and how to interpret relationships between variables. The course covers basic principles of regression methods through to interpreting the output of statistical analyses, and also includes practical sessions giving hands-on experience with regression analysis in R.
Recommended Participants
Researchers who wish to expand their skills into regression methods and who are considering using regression approaches in their research. The workshop is applicable for all disciplines, although examples and exercises will be based around biological datasets. Prior expertise with R and the command line interface is required to a level equivalent of that provided by the “R for Reproducible Scientific Research” workshop, as the basics of R will not be covered. Participants are expected to have a basic familiarity with the concepts of descriptive statistics and elementary statistical hypothesis testing.
Learning Objectives
- Understand the principles of linear regression methods
- Identify the appropriate correlation or regression analysis for a dataset
- Carry out regression analysis using R
- Interpret and report on the results of that analysis
Syllabus
- An introduction to continuous, discontinuous and categorical variables
- Understanding the relationship between variables and plotting that relationship graphically
- Calculating parametric and non-parametric correlation
- Performing simple and multiple linear regression
- Assumptions, errors, and what can go wrong in regression analysis
