Regression in R

Course code
S004
Course fee
Price
€150
Course Level
Master

Linear regression is one of the most ubiquitous statistical methods. Most statistical techniques can be viewed as either special cases of linear regression (e.g., t-tests, ANOVA) or generalisations of linear regression (e.g., multilevel modelling, SEM, neural networks, GLM, survival analysis). In this course, students will learn how to apply linear regression techniques in R. We will cover (multiple) linear regression, categorical predictor variables, moderation, prediction, and diagnostics. Students will practice what they learn via practical exercises.

In the morning/early afternoon, new content will be presented via interactive lectures. In the afternoon, the students will practice what they learned via practical exercises. If the schedule permits, the students are also welcome to ask the instructor for advice on their own data analyses.

  • We will not cover basic R usage. Students should already know how to use R to read and write data, do basic data manipulations, run R functions, and work with the results returned by R functions.
  • Although we will briefly discuss the theory of the methods covered, we will primarily focus on applying these methods in R. So, students should already have some familiarity with the theory of linear regression.
  • We will not cover any generalisations of linear regression such as logistic regression, multilevel modelling, or SEM

.Participants should bring their own computer with both R and RStudio installed.

Course director
Kyle Lang

Lecturers

Kyle Lang

Target audience

Professionals seeking a master-level introduction to linear regression

For an overview of all our summer school courses offered by the Department of Methodology and Statistics please click here.

Aim of the course

After completing this course, students can:

  1. Describe how to apply linear regression in R and choose the correct functions with which to implement a given analysis.
  2. Write basic R scripts to do the following:
  • Run a multiple linear regression model
  • Manipulate the fitted model object produced when estimated a linear regression model
  • Incorporate categorical predictor variables into linear regression models using an appropriate coding scheme
  • Test for moderation using linear regression and conduct a simple slopes analysis
  • Generate predictions by applying a fitted regression model to new data
  • Calculate measures of prediction error to compare the performance of different models
  • Check the assumptions of the linear regression model via model diagnostics

Study load

Approximately 8 hours of classroom time.

Costs

Course fee:
Price
€150
Included:
Fee covers
Course + course materials + lunch
Extra information about the fee

Tuition fee for PhD students from the Faculty of Social and Behavioural Sciences from Utrecht University will be funded by the Graduate School of Social and Behavioural Sciences.

Utrecht Summer School does not offer scholarships for this course.

More information

Irma Reyersen | E: ms.summerschool@uu.nl

Registration

Application deadline: 
Registration deadline
19 January 2022