Professor James Mitchell

Professor of Economics and Finance


Contact Details

  • Tel: 0116 252 2884
  • Email: James Mitchell photo 2011
  • Office: Astley Clarke Building, AC107
  • Office Hours: Thursday 9.30am-11.30am



Research Interests

  • Empirical Macroeconomics; Econometrics


My recent research interests can be divided into four, albeit related, areas.

1. Density forecasting in macro and finance (“fan charts”)

The principal concern is the production, combination and evaluation of so-called density forecasts. Increasingly density forecasts are being considered in economics and finance. This reflects acknowledgment that point forecasts, the traditional focus, are better seen as the central points of ranges of uncertainty. An inflation forecast of, say, 2% must mean that people should not be surprised if actual inflation turns out to be a little larger or smaller than that. To provide a complete description of the uncertainty associated with the point forecast many forecasters therefore now publish density forecasts. A famous example is the Bank of England’s “fan chart”.

More specifically, combination methods have been developed to produce real-time density forecasts robust to a constantly changing economic environment. The density forecasts can be produced using various types of econometric model, including VAR and DSGE models. Related work has considered the ex post evaluation of density forecasts; statistical tests are developed to ascertain whether density forecasts are well-calibrated.

There is considerable scope for a student wishing to develop econometric skills of value to central banks and others to work in this area. The modelling and forecasting of economic and financial variables in probabilistic terms, in the face of uncertainties, is a topic with considerable scope for further research.

2. Short-term forecasting and business cycle analysis

A wide range of both statistical and small-scale structural models are used for short-term “real-time” forecasting (including nowcasting), revisions analysis and “business cycle” analysis. Business cycle analysis involves using econometrics and economic theory, to varying degrees, to isolate from a time-series its “trend” component. Other work includes the production of monthly GDP estimates, from published quarterly data, using interpolation methods. Again the aim is to produce (and then evaluate) data of practical interest to economists using cutting-edge econometric methods.

3. Panel data, including panel qualitative survey data

This work has examined the utility of qualitative business survey data, including expectational data, when nowcasting and forecasting and used these data to better understand expectation formation. In contrast to extant work, the qualitative data are examined at the firm-level rather than at the aggregated-level. Econometric methods have been developed to produce efficient early indicators of macroeconomic aggregates from these panel qualitative data. A recent ESRC project assessed the relationship, at the firm-level, between qualitative business survey data produced by the Confederation of British Industry and official quantitative data collected by the Office for National Statistics. Future work could exploit the increased availability of individual-level data, underlying published macroeconomic statistics, to model and test economic behaviour and theories.

4. Migration

This work develops panel-data econometric models to examine the determinants of and forecast international migration.

PhD Supervision

Happy to supervise a broad range of applied economic and econometric topics.


EC1001:  Macroeconomics 101
EC7075:  International Money and Finance

Selected Publications

  • "Efficient aggregation of panel qualitative survey data", Journal of Applied Econometrics. Forthcoming (with R.J. Smith and M. Weale)
  • "The drivers of international migration to the UK: a panel-based Bayesian model averaging approach", Economic Journal. 2011, 121, 1398–1444 (with N. Pain and R. Riley)
  • "Evaluating density forecasts: forecast combinations, model mixtures, calibration and sharpness", Journal of Applied Econometrics, 2011, 26, 1023-1040 (with K.F. Wallis)
  • "Combining VAR and DSGE Forecast Densities", Journal of Economic Dynamics and Control, 2011, 35, 1659-1670 (with I.W. Bache, A.S. Jore and S.P. Vahey)
  • "Qualitative business surveys: signal or noise?", Journal of the Royal Statistical Society: Series A, 2010, 174, 327-348 (with S. Lui and M. Weale)
  • "Combining forecast densities from VARs with uncertain instabilities", Journal of Applied Econometrics, 2010, 25, 621-634 (with A.S. Jore and S.P. Vahey)
  • "Combining density forecasts" International Journal of Forecasting, 2007, 23, 1-13 (with S.G. Hall)
  • "An Indicator of Monthly GDP and an Early Estimate of Quarterly GDP Growth", Economic Journal, 2005, 115, 108-129 (with R.J. Smith, M. Weale, S. Wright and E.L. Salazar)
  • "Evaluating, comparing and combining density forecasts using the KLIC with an application to the Bank of England and NIESR 'fan' charts of inflation", Oxford Bulletin of Economics and Statistics, 2005, 67, 995-1033 (with S.G. Hall) 
  • "Quantification of qualitative firm-level survey data", Economic Journal, 2002, 112, 117-135 (with R.J. Smith and M. Weale)

Share this page: