Module Directory

This module builds on knowledge that students have gained in GV900 and starts with a refresher on linear regression before delving into more advanced methods, both theoretically and practically. We will start with the assumptions that go into linear regressions, learn to analyse whether each assumption holds and consider how our results are impacted when they do not. We will focus on this both from a theoretical standpoint and learn what diagnostic tests can be used in R to test our regression assumptions. For linear regressions, we will also discuss interaction terms and fixed effects estimation.

The remainder of the module will focus on more advanced statistical methods with a focus on two broad categories. The first will be models for analysing non-continuous dependent variables, including binary, categorical and ordinal dependent variables. As before, we will also focus on how to analyse such data in R.

We will also spend some time introducing students to causal inference methods and analysis, using both observational and experimental data.

Along with the various new statistical techniques that students will learn, they will continue to build their coding skills in R throughout the module. In addition to implementing the statistical models, they will learn more advanced coding skills including writing their own (simple) functions, writing for-loops and nested for-loops, and they will learn to work with messy data so that they gain practical skills that are useful for both academic and non-academic spheres.

The aims of this module are to:

1. Ground students in the language of advanced quantitative research including introductory experimental methods;


2. Equip students with knowledge of a range of advanced statistical techniques including causal inference analyses;


3. Develop students’ ability to present any data in a meaningful and effective manner;


4. Develop students’ ability to comment critically on their own and others’ analyses;


5. Provide training in the advanced use of R;


6. Show students how to build their own datasets.

By the end of this module, students should be able to:

1. Build their own datasets from various sources;


2. Read, understand, and evaluate advanced quantitative analyses published in leading journals;


3. Manipulate data using advanced techniques in R, including writing for-loops and basic functions;


4. Analyse data in R using advanced statistical methods suitable for non-continuous dependent variables;


5. Embark on the more advanced training available to postgraduate students at Essex.

This module will be taught over 2 hours per week