EC349: Data Science for Economists

Jo Turrall
Module Leader

15 CATS - Department of Economics

Introduction

This introductory data science module will introduce core economics students to a wide array of data sources and types and how to work with them. It is intended to provide students with foundation data science skills, working in R.

Principal Aims

The module will introduce students to the meaning of data science, working practically with data in R. Students will learn how to source, manipulate and analyse large data flows, extract knowledge and insights from large, noisy data, and understand how to use these data types to answer certain economics questions. Students will learn to apply data science theorems and algorithms to solve problems using the most suitable software and statistical tools for data processing.

Principal Learning Outcomes

.....understand and apply a range of supervised machine learning techniques—such as LASSO, random forests, boosting, and feedforward neural networks—and use causal inference methods to analyse economic questions. Students will also be able to implement these methods in practice by preparing data, building models, and conducting causal analysis using statistical software such as R or Python.

Syllabus

Topics typically could include, but are not limited to:

1. Introduction: Defining data science, what data scientists do, the data they use, and the limitations of data science.

2. The data science methodology (E.g., CRISM-DM, TDSP, Domino, etc.)

3. Data sources and types – rectangular vs non-rectangular data (e.g., Textual data, multimedia data, spatial-temporal data, click stream data, etc.).

4. Working with data in R

5. Data extraction and acquisition

6. Getting data into shape (mining, wrangling and manipulation)

7. Statistical methods with big data

8. Data visualisation and analysis

9. AI Applications in Data Science (E.g., Supervised Machine learning, Unsupervised Machine Learning, Deep learning, etc.).

10. Data science tools: (E.g., Working with Git, RStudio, Tidyverse, etc.)

11. Data science application in economic analysis – Literature evidence.

Context

Optional Module

L100 - Year 3, L116 - Year 3, LM1D (LLD2) - Year 3, L103 - Year 4, L117 - Year 4, LM1H - Year 4

Pre or Co-requisites

EC203-30 Applied Econometrics OR

EC226-30 Econometrics 1

Summary:

Modules: EC203-30 or EC226-30

Assessment

Assessment Method: Coursework (40%) + Centrally-timetabled examination (On-campus) (60%)
Coursework Details: Centrally-timetabled examination (On-campus) (60%) , Individual Project (40%)
Exam Timing: Summer