Module Details

BE333-6-SP-CO: Empirical Finance

Note: This module is inactive. Visit the Module Directory to view modules and variants offered during the current academic year.

Year: 2016/17
Department: Essex Business School
Essex credit: 15
ECTS credit: 7.5
Available to Study Abroad / Exchange Students: Yes
Full Year Module Available to Study Abroad / Exchange Students for a Single Term: No
Outside Option: Yes
Pre-requisites: BE314 OR EC252
Co-requisites:

Staff
Supervisor: Sina Erdal
Teaching Staff: Sina Erdal
Contact details: ebsugcol@essex.ac.uk

Module is taught during the following terms
Autumn Spring Summer

Module Description

This module builds on the second-year module, BE314 Financial Modelling, to deepen students' understanding of Ordinary Least Squares (OLS) estimation. The emphasis is on the pitfalls of OLS and problems with data. Problems and issues frequently encountered in practice, such as non-linear data generating processes, heteroscedasticity, autocorrelation and unit roots are examined. In each case, we start off by defining the problem at hand, move on to how OLS results and prediction might be affected if the problem goes undetected, discuss the commonly employed tests for detection, and end with a discussion of corrective action. The context is topics from Finance, and we make extensive use of the software package Eviews to run models with real financial data.

Learning Aims and Outcomes

After completing this Module students should be able to:
1. Set up an OLS model to estimate a linear relationship between a set of variables. Be able to interpret all items in an OLS output.
2. Work with non-linear but linearisable data generating processes and estimate models based on them using OLS.
3. Describe in detail the problems such as heteroscedasticity and autocorrelation that have to be dealt with when performing OLS estimation. Be able to perform diagnostic tests and take corrective actions.
4. Set up a time series model. Describe in detail how non-stationarity affects the outcome of time series estimation. Be able to detect and correct for non-stationarity in the data.
5. Achieve proficiency in Eviews.

Learning and Teaching Methods

There will be a two-hour lecture per week for ten consecutive weeks and a one-hour computer lab per week for nine consecutive weeks. Labs are absolutely essential for the learning process and the value added of this module. You are expected to do the relevant reading and preparation before each lecture and lab. Each lab shall consist of a number of tasks that relate to the preceding lectures. Although teaching staff will be available to answer queries you will nevertheless be expected to work independently during the labs.

Assessment

30 per cent Coursework Mark, 70 per cent Exam Mark

Coursework

Coursework - one individual research paper to be handed in at the end of the term (30%)

Exam Duration and Period

2:00 during Summer Examination period.

Further information