This intensive four-day course is aimed at students and researchers who have already taken an introductory course in statistics and wish to learn more about how to use linear regression – one of the key tools in the applied quantitative researcher’s toolkit – in their own research. The course will involve a mixture of teaching and participants working on real data analysis projects. It will be taught using the open source statistics software R, thus introducing participants to one of the most powerful and flexible statistical computing packages. Students who take this course can expect to learn about:

• The basics of the R environment
• The fundamentals of simple and multiple linear regression: Assumptions, estimation, interpretation and presentation of results
• How to explore your data before fitting regression models
• Fitting an appropriate regression model to your data: regression diagnostics, variable transformations and model building
• Modelling interactions between variables within the regression framework

*** This course assumes participants have knowledge of basic statistics. Please only sign up if you have already taken the CARD course “GD447: Introduction to Applied Quantitative Data Analysis for the Social Sciences and Humanities”, or another introductory statistics course covering basic analysis of statistical association and statistical inference using significance tests and confidence intervals. We may ask applicants to provide details of their prior training before offering places on the course.

*** The course does not assume participants have experience of using R

Because the aim of the course is to develop an applied understanding of statistical methods, we will not rely heavily on maths. However, we will sometimes use simple mathematical formulae to convey the logic of a statistical method. In these instances, these formulae will be explained as fully as possible.

We expect all participants to attend the entire course. Please only sign up for this course if you are able to do so.