This double module provides students pursuing the Economics and related schemes with the core techniques used in the analysis of both cross section and time series economic data.  Study of the theory is reinforced with instruction in and use of modern econometric software.

The aims of this module are firstly to enable students to acquire competence in the use of economic data for the analysis of issues and questions in economics and secondly to develop an awareness of the limitations of such uses.

A    Knowledge and Understanding:

• explain and critically appraise the relevance to economic data of all the terms and concepts associated with the Classical Regression Model.
• know how to select an appropriate functional form to represent an economic relationship.
• explain and contrast principles of parameter estimation based on fit with those based on likelihood.
• explain, compute and interpret statistical tests of composite hypotheses, omitted and irrelevant variables and of model stability.
• describe how economic variables with limited values may be incorporated into regression models.
• define the nature of and apply procedures for dealing with commonly occurring residual error structures.
• explain the identification problem and apply procedures for the estimation of parameters in simultaneous equation models.
• explain and contrast causal and ARIMA lag representations of mid-frequency time series data.
• explain and apply valid procedures for the application of regression methods to time series data.

B    Intellectual Skills: 

• synthesise and evaluate the technical concepts of the syllabus
• appraise theory and its relevance to different situations
• plan, design and investigate a computer simulation
• critically compare the results of data analysis with model expectations

C    Discipline Specific Skills: 

• compute and interpret estimates and inferential statistics associated with the two- and three- variable Classical Regression Model.
• use Econometric software (Eviews) interactively to analyse supplied datasets in support of the learning outcomes identified above.
• work together to program econometric software (Eviews) to carry out a Monte Carlo study of an econometric estimator.

D    Transferable Skills: 

• working with others to develop a computer based investigation
• prepare reports integrating textual and numerical material
• develop personal management skills associated with working to a deadline
• finding data using both traditional and ‘web’ sources

Teaching takes place in both the first and second semesters.  In each semester there are 11 weekly 50-minute lectures and 11 weekly 50-minute computer lab sessions.  The lectures cover the methodology and techniques aspects of the syllabus whilst the lab sessions provide opportunities for application, discussion and reinforcement of the lecture material as well as giving experience using a ‘state of the art’ econometrics computer package.

Lectures are supported with detailed handouts, OHP slides and computer demonstrations where appropriate.  Use of the dedicated software offers an appreciation of the advantages and disadvantages of interactive and programming interfaces for econometric research.  The lab sessions are supported by offering each student networked access to the specialist econometric software, spreadsheet software for data management, word-processing software for report writing, E-mail for virtual learning environment and the Internet for data sources.

Indicative study hours:   200

The examination paper is made up of two sections.  In the first, a single compulsory question requires the student to write briefly demonstrating their understanding of the meaning and importance of three out of four nominated technical terms at the root of the econometrics syllabus.  The second section requires the student to select three questions from those offered to show a deeper understanding of and ability to apply the topics covered in the module.

The continuously assessed component comprises two projects each contributing 20% of the assessment.  

(Sem1) The methodology of econometrics and basic matrix algebra form.  Three methods to tackle the linear regression model: least squares, method of moments, maximum likelihood.  Large sample statistical theory.  Monte Carlo methods.  Robust variance estimation.  Omitted variable bias and proxy variable.  Instrumental variable estimation and generalized method of moments.

(Sem2)  Linear probability models and limited dependent variable models.  Simultaneous equations models.  Stationary and trend stationary time series models.  Analysis of nonstationary time series and unit root processes.

J.M. Wooldridge “Introductory Econometrics: A Modern Approach” (4^th Edition) South Western College, Learning, 2008

J.H. Stock and M.W. Watson “Introduction to Econometrics” (2^nd edition), 2006

G. S. Maddala, “Introduction to Econometrics” (4^th edition) John Wiley & Sons, 2009

G. Koop “Introduction to Econometrics”, 2008, John Wiley & Sons