Module description
What is the module about?
This module introduces students to the main techniques that economists use for estimating economic relationships, testing economic theories and evaluating government and business policies.
We cover the fundamentals of linear regression analysis as well as more advanced topics related to estimation and inference for probability models, panel and time series data. Throughout the module, we study examples based on real data and published research. In class, we do some number crunching ourselves using Stata, a fast and versatile software for quantitative research and we will have 5 workshops throughout the Semester in addition to tutorials and lectures.
Our ultimate goal in this module is to learn how to use data to answer causal if-then questions, i.e. to make predictions under plausible assumptions, consistent with the available evidence.
Who should do this module?
It should be of interest to students who want a deeper understanding of quantitative methods.
Provisional Lecture Outline
Lecture 1: Introduction to linear regression
Lecture 2: Simple linear regression I: Assumptions and Estimation
Lecture 3: Simple linear regression II: Interpretation and Inference
Lecture 4: Multiple regression I: Omitted variable bias, inference, interpretation
Lecture 5: Multiple regression II: Non-linear functions
Lecture 6: Instrumental Variables
Lecture 7: Panel data I: fixed effects
Lecture 8: Panel data II: random effects
Lecture 9: Probability models
Lecture 10: Applications: prediction with many regressors and Big Data
Assessment details
80% Examination
20% Individual Coursework
The format of the examination has not yet been confirmed. All students will be expected to sit any remote exams in January, but semester 1 only students will be set an alternative assessment in lieu of in-person exams
Teaching pattern
Fortnightly Workshops
Weekly Tutorial
Suggested reading list
J.H. Stock and M.W. Watson, Introduction to Econometrics, 4th edition, Pearson 2020