Department of Economics



The Econometrics Research Group was established in February 2014. Its purpose is to provide a scientific forum for doctoral students and members of staff of the Department of Economics whose research interests involve applied econometrics and econometric theory.

Members of the Group both publish in top economics journals, such as the Journal of EconometricsEconometric Theory, the Review of Financial Studies, the Journal of Money, Credit and Banking as well as present their work in international conferences such as the Econometric Society, the Royal Economic Society, the American Statistical Association, the Society for Economic Measurement and the German Statistical Society (DStatG).


Research focus

Currently the work of the Group’s members lies in the broad area of time series econometrics with applications in finance and macroeconomics.

Some research themes on which we are focusing at the present are testing of the presence of asymmetric effects on shocks of economic and financial time series (linear and non-linear) models, the development of robust test statistics and the detection and estimation of structural change. We apply these methods to asset pricing and macro-econometric models.

Research staff

Internal group members

Dr Andreea Halunga’s (group leader) research is about misspecification/specification testing in econometric models. Her work is also concerned with the asymptotic theory analysis and applications of bootstrap techniques in capturing time series changes such as changes in persistence and structural breaks. She has published in the Journal of Econometrics, Econometric Theory and Economics Letters. Current research projects involve developing ratio-based test procedures for detecting changes in persistence allowing for possible structural breaks, asymptotic theory for misspecification testing in Realized GARCH models and robust heteroskedasticity tests for contemporaneous correlation in dynamic panel data models.

Dr Bruce Morley is currently working on the UK housing market project with a colleague, focusing in particular on asymmetric adjustment between house prices and macroeconomic fundamentals. This will allow us to determine whether policy makers intervene more in the housing market when house prices are below equilibrium as opposed to when they are above it. If there is asymmetry, it suggests the authorities are concerned with falling housing markets but are happy to allow speculative bubbles to form, as there is less evidence of adjustment when house prices are high.

Dr Nikos Sakkas is researching Time Series econometrics and in particular the modelling and inference issues that result from structural change in economic models. Currently he is working on using Information Criteria methods to detect structural breaks in linear and non-linear models allowing for multiple unknown change points. This involves establishing the limiting properties and evaluating the finite sample performance of these procedures. He is also working on applying the above to macroeconomic models such as Taylor rules and Phillips Curves allowing for conditions such as endogeneity, multiple structural change, or non-linearity.

Dr Imran Shah is currently working on the paper ‘Making the most of high inflation’ jointly with Wojciech W. Charemza (University of Leicester) and Svetlana Makarova (UCL). The paper conjectured that, in countries with frequent episodes of high inflation, output stimulation through positive inflationary shocks increases with the increase in the differences between the expected and output-neutral inflation. It is shown that this conjecture is valid for most countries with high inflation episodes, in which inflation is greater than 4.8% for at least 25% of quarterly observations. This leads to simple policy prescriptions that, in economies with high inflation episodes, anti-inflationary monetary decisions are most effective for output when the differences between the expected inflation and output-neutral are the smallest.

External group members

Dr Michalis Stamatogiannis is currently working on the predictability of stock returns, which is a fundamental issue in asset pricing. The conclusions of empirical analyses on the existence of stock return predictability vary according to the time series properties of the economic variables considered as potential predictors. Given the uncertainty about the persistence of these variables, it is important to operate in the most general possible modelling framework. The IVX methodology provides such a framework in the context of cointegrated systems with no deterministic components. This method is modified in order to apply to multivariate systems of predictive regressions with an intercept in the model. The resulting modified IVX approach yields chi-squared inference for general linear restrictions on the regression coefficients that is robust to the degree of persistence of the predictor variables. In addition to extending the class of generating mechanisms for predictive regression, the approach extends the range of testable hypotheses, assessing the combined effects of different explanatory variables to stock returns rather than the individual effect of each explanatory variable.

Recent research output