Marco Fioramanti, Robert Waldmann, 19 November 2016

The European Commission is currently evaluating compliance with the Stability and Growth Pact across the Eurozone. However, differences in the econometric methods used by member states and by the Commission can lead to estimates that are at odds. This column argues that the Commission’s method of estimating the non-accelerating wage rate of unemployment for Eurozone members, which relies on an accelerationist Phillips curve, is inferior to specifications with a traditional Phillips curve. The findings highlight how technical aspects of an estimation procedure can have serious effects on policy outcomes.

Bruce Hansen, 03 June 2016

If an economist selects the wrong model to study a question, the results are also likely to be wrong. In this video, Bruce Hansen talks to Soumaya Keynes about how model selection and combination can be used for forecasting with small error. Model combination methods are suited for forecasting and policy evaluation. This video was recorded in March 2016 during the Royal Economic Society’s Annual Conference held at the University of Sussex.

Christian Hansen, 27 May 2016

Big data is changing economics and the way causal relationships are studied. In this video, Christian Hansen and Soumaya Keynes discuss the importance of big data for econometrics. Big data offers a lot of information and it is easier to draw policy lessons. It also gives more flexibility without forcing researchers to impose control variables, allowing more reliable conclusions to be obtained. This video was recorded in March 2016 during the Royal Economic Society’s Annual Conference held at the University of Sussex.

Paolo Mauro, Jan Zilinsky, 18 September 2015

The public narrative on austerity is shaped by simple scatter plots purporting to portray the large negative impact of fiscal ‘austerity’ on economic growth. This column argues that, while recognising concerns about causality, economists should systematically explore correlations and multiple regressions, and test their robustness. The results reveal a mixed picture, lending partial support to the notion that fiscal choices and output growth are empirically associated.

Josh Angrist, Jörn-Steffen Pischke, 21 May 2015

Economic scholarship has changed dramatically in the past half-century, becoming far more empirical and much less abstract and theoretical. The winds of change have blown most strongly in applied microeconomics, but econometrics has been left far behind. This column argues that econometrics teaching needs an overhaul and that this change has to start with better textbooks.

Jennifer Castle, David Hendry, 13 August 2014

A typical Oxford University econometrics exam question might take the form: “Data mining is bad, so mining with more candidate variables than observations must be pernicious. Discuss.” Similar questions may well be asked at other academic institutions, but there may be few outside Oxford University where the candidates are expected to refute both myths. This column explains why that is the right answer.

Manfred Gilli, Peter Winker, 11 October 2008

Many optimisation problems in economics cannot be solved with standard methods due to discontinuities and the existence of multiple optima. This column introduces heuristic optimisation, which offers a solution in such cases.