Accessibility statement

Econometrics for Research - ECO00002D

« Back to module search

  • Department: Economics and Related Studies
  • Module co-ordinator: Prof. Laura Coroneo
  • Credit value: 20 credits
  • Credit level: D
  • Academic year of delivery: 2022-23
    • See module specification for other years: 2021-22

Module summary

The module provides an advanced treatment of selected topics on Applied Econometrics.  Topics and teachers change from year to year.

Module will run

Occurrence Teaching period
A Autumn Term 2022-23 to Spring Term 2022-23

Module aims

  • A set of specialist lectures specialising in Econometric Theory
  • A complementary set of practical classes to teach the implementation of applied econometrics

Module learning outcomes

The topics taught in Applied Econometrics for Research can change from year to year, depending on what is considered to be most relevant and up to date. Objectives in the past year were:

1. Programme Evaluation

  • Introduction to programme evaluation. Recent decades has seen a surge in econometric methods for programme evaluation. The objective is to estimate the causal effect of a policy. The course will set out the econometric problem and detail different methods that have been established to identify the causal parameter.
  • Methods including experiments, natural experiments, matching, propensity score matching, IV and difference-in-difference

2. Panel Data

  • Panel data offer the scope to control for individual heterogeneity and to model the dynamics of individual behaviour. However the measures of outcome used in applied microeconomics are often qualitative or categorical. These create special problems for estimating econometric models. This topic focuses on binary choice models for panel data. Practical application of the methods will be illustrated using data on health from the British Household Panel Survey (BHPS).
  • GVAR. The introduction of the panel and global VAR frameworks and the increasing sophistication of large simulated systems provides opportunities to analyse international linkages in unprecedented depth. The GVAR model represents an accessible way of combining country-specific models into a global framework without falling victim to the dimensional problems typically associated with such large-scale models. The ability to coherently model the global economy and to assess the effects on a sovereign state/economic bloc, both of global shocks and of shocks emanating from specific countries, renders GVAR an unusually powerful tool for the analysis of the number of macroeconomic issues. However, the considerable volume of statistical output generated by such models introduces a secondary curse of dimensionality, whereby the limits of the modellers ability to process the output become a binding constraint. We also develop a family of Generalized Connectedness Measures (GCMs) which provide a simple means to summarise the linkages embodied in such models non-selectively either with recourse to geographic aggregation or aggregation into desired groups of similar variables.

3. Cross-Sectionally Correlated Data

  • Spatial Econometrics: Discuss the development of the leading models employed to handle situations in which spatially structured interactions between observational units (spillovers or flows) are at the core of the analysis. If time allows, both so-called spatial autoregression models and the gravity model will be discussed, and some model specification issues will be introduced that either are, or should be, the subject of current research
  • Topics on estimation and inference in some static linear panel data models. In this session, after briefly reviewing the famous Fixed Effects (FE) and Random Effects (RE) estimators, we plan to discuss various econometric methods for estimation and inference of static linear short panel data models, which are extensions of the FE and RE models. The econometric methods include the instrumental variable (IV) estimator of Hausman and Taylor (1981) for the models with endogenous individual effects and the Generalised Method of Moments (GMM) estimator of Ahn, Lee and Schmidt (2013) for the models with endogenous interactive effects. We also introduce the methods of Pesaran (2006) and Bai (2009) for static linear large panel data models under multi-factor error structure. In the practical session, applications of some of these estimation methods will be illustrated.

Indicative assessment

Task Length % of module mark
Essay/coursework
Essay		 N/A 100

Special assessment rules

None

Indicative reassessment

Task Length % of module mark
Essay/coursework
Essay		 N/A 100

Module feedback

Feedback will be provided in line with University guidelines.

Indicative reading

A list of readings will be suggested during lectures for each specific econometric topic.


The information on this page is indicative of the module that is currently on offer. The University constantly explores ways to enhance and improve its degree programmes and therefore reserves the right to make variations to the content and method of delivery of modules, and to discontinue modules, if such action is reasonably considered to be necessary. In some instances it may be appropriate for the University to notify and consult with affected students about module changes in accordance with the University's policy on the Approval of Modifications to Existing Taught Programmes of Study.