Primary: Econometric Theory and Applications (principally Time Series).
Secondary: Macro/Financial Econometrics (in particular, commodity prices and exchange rates).
My recent working papers can be found using the following button:
"GLS Detrending in Continuous Time," currently under revision.
"Time-Varying Parameters and Heteroskedasticity: Continuous Time Systems with Unequally-Spaced Data" (with H Zhang).
A full list of my publications can be found using the button below:
The Analysis of Non-stationary Time Series in Economics and Finance: Cointegration, Trend Breaks, and Mixed Frequency
Data (with AM Robert Taylor, Essex Business School) (Award Number ES/M01147X/1, October 2015-September 2017).
Further details can be found below or on Rob's webpages here.
The Analysis of Non-stationary Time Series in Economics and Finance: Cointegration, Trend Breaks, and Mixed Frequency Data
Principal Investigator: A.M. Robert Taylor, Essex Business School, University of Essex
Co-Investigator: Marcus J. Chambers, Department of Economics, University of Essex
Macroeconomic and financial time series are typically non-stationary (or unstable), in that their means, variances and autocovariances evolve over time. As a result standard multivariate time series models can only be validly applied to the changes in these variables. Such models, however, contain no information about any long run relationships between the series, as are often predicted by economic or finance theory. A solution is provided by co-integration analysis which recognises that certain combinations of the variables are stationary (stable). A key example is term structure data, where it is often found that while individual interest rates appear to be unstable, the spreads between the rates appear stable.
Practical co-integration analysis is complicated by the fact that economies periodically undergo episodes of structural change, such as stock market crashes or changes in government regime/policy. Empirical evidence suggests that these episodes often manifest themselves in the form of multiple changes in the underlying deterministic trend component of the variables and/or changes in the volatility of the unanticipated random shocks. Extant co-integration tests can result in misleading inference regarding the presence or otherwise of long run relationships between the variables when these forms of structural change are present. This will typically result in misspecified econometric models with poor forecasting ability. It is therefore important to develop new co-integration tests which can deliver reliable inference in such environments. Doing so constitutes the first part of this project and will involve the development of a new simulation-based (bootstrap) procedure.
In light of the recent financial crisis, attention has increasingly focused on understanding the interactions between the macroeconomy and the financial sector. To do so effectively, econometric methods are needed that are capable of handling the mismatch between the frequencies at which data on the financial sector (eg exchange rates, stock prices) and the macroeconomy (eg GDP) become available, and this constitutes the second part of the project. While financial data can be observed at very high frequencies, macroeconomic data are typically available only monthly at best. The vast majority of methods for modelling multivariate time series assume a common sampling frequency; this typically entails discarding information in the high frequency data by converting it to the lowest frequency. However, high frequency financial data contains information that can affect the future time path of the low frequency data, and its utilisation can enable policymakers to act promptly prior to the macroeconomic data becoming available. For example, a financial crisis can be observed long before its effects on GDP are observed, but the ability to predict what those effects might be, using an econometric model capable of dealing with mixed frequency data, can be an important aid to policy making. Methods to allow for structural changes when dealing with mixed frequency data will also be considered.
The theoretical development, to be conducted using large sample econometric theory, will exploit the expertise and experience of the applicants. Taylor has already examined the behaviour of non-constant volatility on co-integration tests which do not allow for structural change in the trend. Chambers has recently developed methods of combining mixed frequency data that preserve the underlying relationships between the series and has also analysed co-integrated systems under temporal aggregation. This project will build on these foundations.
The practical relevance of the theoretical results will be explored using simulation experiments. We will also provide clear guidance to empirical researchers, through worked examples on key international datasets, and make freely available computer programs, to facilitate the implementation of the new techniques.
A full list of outputs produced by Rob and me can be found on his pages here.
The first of two one-day workshops took place at Essex on Monday 11 July, 2016 on the theme of "Co-integration, Multivariate Time Series Modelling and Structural Change"; the workshop programme is available here.
The second one-day workshop took place at Essex on Wednesday 5 July, 2017 on the theme of "Econometric Modelling with Mixed Frequency and Aggregated Data"; the workshop programme is available here.
For contact details please see the main page of this website.
Jackknife Methods of Estimation and Inference in Dynamic Econometric Models (Award Number RES-000-22-3082,
September 2008-December 2009).
Further details can be found below:
Jackknife Methods of Estimation and Inference in Dynamic Econometric Models
Marcus J. Chambers, University of Essex (Award Number RES-000-22-3082)
Time series data in economics, finance and many other disciplines, are typically characterised by high degrees of correlation over time, and dynamic models that relate variables to their past values are in widespread use in the modelling and forecasting of such data. In samples of fixed size, however, estimators of the unknown parameters in such models are typically biased and can lead to misleading interpretations of the observed data and to inaccurate (and potentially costly) forecasts. The jackknife method of bias reduction was developed for use with random (uncorrelated) samples but, with suitable modifications, it can also be used with time series data; this research project will analyse and develop jackknife methods in dynamic models of the types used in both theoretical and empirical research in econometrics. In particular the research will analyse the performance of jackknife bias reduction methods in stationary and nonstationary time series models and evaluate their effects on related statistical hypothesis tests. The effectiveness of the jackknife with different estimation methods and on the accuracy of post-sample forecasts will also be explored. A combination of analytical statistical and econometric techniques will be used combined with appropriately designed computer simulations and applications to relevant data.
Some Gauss code to calculate the jackknife estimator in a linear regression model and a univariate AR(1) is contained in the following file: (.src)
For contact details please see the main page of this website.