EC910: Quantitative Methods: Econometrics B

Han Zhang
Module Leader

45 CATS - Department of Economics

Introduction

The module provides students with a thorough understanding of material needed for empirical quantitative analysis, particularly applied econometrics. You will understand how to produce high quality empirical econometric analysis using cross-sectional, time-series, and panel data, and also learn to interpret critically empirical results.

Principal Aims

The aim of the module is to give students a good grounding in maths, statistics and modern econometric techniques. Within the econometrics element, students will study the ways in which the techniques are applied in the empirical analysis of economic data. This module will supplement the development of these key and fundamental professional skills, by looking at more advanced topics.

Principal Learning Outcomes

Subject Knowledge and Understanding: demonstrate an understanding of fundamental concepts in mathematics and statistics relevant to the other core modules and be able to apply these concepts to economics.

Subject Knowledge and Understanding: demonstrate a deep understanding of material needed for empirical quantitative analysis.

Subject Specific and Professional Skills: demonstrate a full knowledge of the theory and practice of modern econometrics, particularly applied econometrics.

Cognitive Skills: interpret critically empirical results, including the vast array of diagnostic and test statistics often reported, and to come to a balanced view concerning the weight of the empirical evidence presented.

Syllabus

The syllabus for this module will be based on the following topics; however this list is not limited to those listed below and does not infer all of these topics will be studied in the module:

Introductory Mathematics and Statistics: pre-sessional topics covered will include linear algebra, multivariate calculus and constrained optimisation, differential and difference equations, basic probability theory and hypothesis testing.

The first term will emphasise microeconometric applications, and will cover: properties of estimators and how to generate different estimators (Maximum Likelihood Estimation, least squares, method of moments); discrete choice models (binary, unordered multinomial); censored and truncated dependent variable models (Tobit, endogenous selection - Heckman, switching regression models); Linear panel data models; Treatment evaluation methods.

The second term covers structural econometric modelling (endogeneity and instrumental variables) as well as time series econometrics for macroeconometrics and finance. This will include the investigation of dynamic econometric modelling based on ARMA, GARCH, Vector AutoRegression, Stochastic Volatility and State Space models.

Inference techniques include Maximum Likelihood, Generalized Method of Moments and Simulation-based Inference.

Context

Core Module: L1I1 - Year 1
Optional Core Module: L1P6 - Year 1, L1P7 - Year 1
Optional Module: G30A - Year 4, G30B - Year 4
Pre or Co-requisites: An undergraduate module in introductory econometrics and basic knowledge of matrix algebra.

Assessment

Assessment Method: Coursework (45%) + Centrally-timetabled examination (On-campus) (55%)
Coursework Details: Centrally-timetabled examination (On-campus) (55%) , Group Project (25%) , Test 1 (4%) , Test 2 (6%) , Test 3 (10%)
Exam Timing: Summer