Title: Hyper-parameterised dynamic regressions for nowcasting Spanish GDP growth in real time

Authors: David De Antonio Liedo; Elena Fernández Muñoz

Addresses: National Bank of Belgium, Research and Development (Statistics), Boulevard de Berlaimont 14, 1000, Brussels, Belgium ' I.E.S. Brianda de Mendoza, Economics Department, Calle de los Hermanos, Fernández Galiano 6, 19004, Guadalajara, Spain

Abstract: This paper analyses the nowcasting performance of hyper-parameterised dynamic regression models with a large number of variables in log levels, and compares it with state-of-the-art methods for nowcasting. We deal with the 'curse of dimensionality' by exploiting prior information originating in the Bayesian VAR literature. The real-time forecast simulation conducted over the most severe phase of the Great Recession shows that our method yields reliable GDP predictions almost one and a half months before the official figures are published. The usefulness of our approach is confirmed in a genuine out-of-sample evaluation over the European sovereign debt crisis and subsequent recovery.

Keywords: Bayesian shrinkage; VAR; value-at-risk; co-movements; mixed estimation; prior elicitation; dynamic factor models; nowcasting plugin; JDemetra+; hyper-parameterised dynamic regressions; Spain; GDP growth; gross domestic product; real time; modelling; curse of dimensionality; simulation; European sovereign debt crisis; GDP forecasting.

DOI: 10.1504/IJCEE.2017.10000659

International Journal of Computational Economics and Econometrics, 2017 Vol.7 No.1/2, pp.5 - 42

Accepted: 11 Jul 2016
Published online: 01 Dec 2016 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article