Install the app
Install this application on your home screen for quick and easy access when you’re on the go.
Just tap then “Add to Home Screen”
Install this application on your home screen for quick and easy access when you’re on the go.
Just tap then “Add to Home Screen”
Menu
Install this application on your home screen for quick and easy access when you’re on the go.
Just tap then “Add to Home Screen”
Monday 6 – Friday 10 February 2023
Minimum 2 hours of live teaching per day
09:30 – 12:00 CET
This course provides a highly interactive blended learning environment, using state-of-the-art online and in-person pedagogical tools. Prior to the live course, you will have access to online videos and tools to help us go deeper into the material during our live sessions. The course is designed for a demanding audience (researchers, professional analysts, advanced students) and capped at a maximum of 16 participants so that the teaching team can cater to the specific needs of each individual.
This course offers an introduction to regression analysis using R (one of the most versatile and popular programming languages). You will learn the classical theory of Ordinary Least Squares (OLS) regression, as well as non-linear regression techniques. You will use a variety of data and models to show when and how regression can be useful in policy analysis, and other contexts.
3 credits Engage fully with class activities
4 credits Complete a post-class assignment
Alexandru Moise is a postdoctoral researcher at the European University Institute (2020–2025). He received his PhD in political science from Central European University in 2019. Alex's research focus is the political economy of welfare reforms. He looks at how individual perceptions and the quality of party linkages affect health care policy. Within the context of the ERC SOLID project, he looks at how crises affect European integration using a variety of quantitative models. He has been teaching quantitative analysis courses at Johns Hopkins University, the European University Institute, Central European University, Ilija University, and the ECPR’s Summer and Winter Schools for many years.
Regression is the main workhorse of statistical analysis. A solid understanding of regression will pave the way to understanding and using more sophisticated modelling techniques.
A very brief overview of the necessary ingredients from probability and statistics. You will learn the basic functionality of the statistical software R through application, starting with the generation of descriptive statistics and graphics.
You will begin with the simple regression model, starting with a theoretical derivation of coefficient estimates in the Ordinary Least Squares (OLS) regression model and an overview of its properties. The group will discuss assumptions that underline the validity of a simple linear regression model.
Once you have gained a solid understanding of the simple linear regression model, we move on to statistical inference.
We cover multiple linear regression, which allows for more than one explanatory variable. Within the context of multiple regression, you will pay particular attention to identifying models that provide the most credible estimate of the explanatory variable of interest.
We briefly introduce non-linear regression models, along with some other more advanced regression techniques.
Online pre-course materials can be accessed at your own pace. Readings are supplemented with around four hours of pre-recorded lectures and interactive R notebooks.
The videos will help you start exploring R before the live sessions. You can keep all course materials for future reference. The videos will walk you through how to make a local install of R Studio.
Pre-recorded lectures will introduce the major topics we will discuss in detail during the course. Similarly, R notebooks let you explore R at your own pace, but we will go through the code and models together during the live sessions. We will set up Canvas forums for each topic where you can discuss, share code and ask questions!
During the course week, expect to be in class on campus for over ten hours in total. We will get to know each other and each other's projects, and explore how we can apply regression analysis to answer relevant questions in political science. The Instructor and TA will work with you to tackle the theoretical problems you might face in designing your analysis. They will also help you use R to manipulate data, program models, and to visualise data and results.
During the course week you will complete assignments to test the knowledge you have gained. We will discuss these assignments, and any problems you may have, together.
The Instructors will host Q&A sessions and social breaks. We will also designate ‘office hours’, during which you can sign up for a quick one-to-one consultation.
This course requires a basic understanding of probability. Basic knowledge of R would also be useful. If you don't have this knowledge, consider taking the courses Introduction to R and Introduction to Inferential Statistics.
You must complete up to ten hours' preparatory work. This includes: