Skip to main navigationSkip to main content
The University of Southampton
Courses

ECON3040 Advanced Econometrics with Machine Learning

Module Overview

Building on the econometric content learned in the second year this module introduces students to advanced topics in econometrics. The module will familiarise students with state of the art methods of model selection in econometrics, giving them access to the fundamental methods in machine learning relevant for statistical inference in economic contexts. It will also introduce students to frontier methods in causal inference to enable meaningful policy evaluation. Applications to economic problem will be used throughout to illustrate the methods.

Aims and Objectives

Learning Outcomes

Knowledge and Understanding

Having successfully completed this module, you will be able to demonstrate knowledge and understanding of:

  • methods of machine learning and model selection.
  • fundamental machine learning methods for quantitative economic and econometric analysis.
  • implementing machine learning techniques using adequate computational tools.
Subject Specific Intellectual and Research Skills

Having successfully completed this module you will be able to:

  • apply economic logical analysis to econometric models of machine learning for the identification of causal inference
  • use model selection methods to organise and analyse economic data in an informative manner.
  • use data, including from large datasets, for statistical inference on the quantitative or qualitative workings of economic mechanisms and policies.
  • use programming techniques from machine learning for data analysis
Transferable and Generic Skills

Having successfully completed this module you will be able to:

  • use quantitative reasoning and analyse and interpret data using machine learning
  • collaborate with others and recognise problems of and possible solutions for structuring team work in a data analysis project

Syllabus

After a brief review of the relevant fundamental econometric methodology the module will cover in depth various methods of model selection such as LASSO and random forests and give a thorough introduction to algorithmic model selection. The module will also cover key topics in causal inference. The methods will be applied to address economic policy questions, retrieving and manipulating large datasets from sources as necessary.

Learning and Teaching

Teaching and learning methods

Lectures and (computer-based) Masterclasses

TypeHours
Tutorial8
Independent Study120
Lecture20
Workshops2
Total study time150

Resources & Reading list

Lecture Notes on Blackboard.

Assessment

Assessment Strategy

Continuous assessment through three take-home data analysis assignments, supported by continuous formative assessment through data analysis exercises. There is no final exam. This is the same for an internal repeat. Assessment for external repeat and referral is through a single piece of coursework.

Summative

MethodPercentage contribution
Coursework assignment(s) 10%
Coursework assignment(s) 15%
Coursework assignment(s) 70%
Online test 5%

Repeat

MethodPercentage contribution
Coursework assignment(s) 100%

Referral

MethodPercentage contribution
Coursework assignment(s) 100%

Repeat Information

Repeat type: Internal & External

Linked modules

Pre-requisites

To study this module, you will need to have studied the following module(s):

CodeModule
ECON2040Computational Economics
Share this module Share this on Facebook Share this on Twitter Share this on Weibo
Privacy Settings