Statistical methods for use in economics and finance
Nonparametric and semiparametric statistical methods contribute to reducing the strength of the assumptions required for estimation and inference. This helps to minimise misleading results. These methods can be applied to a broad range of estimation problems in economics and finance. What is more, they are increasingly being used in applied research. With this in mind, the EU-funded NAMSEF (Nonparametric and semiparametric methods in economics and finance) project set out to develop a nonparametric methodology for applications in economics and finance. The first part of the project focused on separable nonparametric models, widely considered as being at the frontier of econometric methodology. The second and final phase centred around the testing of stochastic dominance, a method that is receiving much interest for its applications in various situations, including finance, risk and economics. To this effect, project partners further expanded the existing methodology and its application to new problems. For the separable nonparametric models and stochastic dominance, the NAMSEF team defined estimators and test statistics, and then analysed their properties. It also applied the methodology to both simulated and real data by developing efficient computer programmes and running them on advanced machines. Several papers featuring key research outcomes were published in leading academic journals, particularly on developing nonparametric methodology for applications in economics and finance. NAMSEF presented the main ideas underlying nonparametric and semiparametric methods, and successfully introduced a nonparametric methodology that can be used in economics and finance.
