This paper introduces the new Monthly Index of Business Activity (MIBA) model of the Banque de France for forecasting France's GDP. As the previous versions, the model relies exclusively on data from the monthly business survey (EMC) conducted by the Banque de France. However, several major changes have been implemented in the present version, such as the shift from a model based on factors to a model based on survey opinions, the explicit targeting of first-release GDP, and the use of the “blocking” approach to deal with mixed frequencies and missing observations. The selected monthly equations are consistent with the time frame of real-time forecasting exercises: the first month equation is dominated by data on expected evolution of the economic activity across the coincident quarter, while for the second and third month equations data on observed economic activity become more important and forward-looking information is progressively discarded. Finally, out-of-sample results suggest that the new MIBA model broadly outperforms several competing models, such as the previous version of MIBA and models based on alternative specifications.
Matteo Mogliani, Véronique Brunhes-Lesage, Olivier Darné and Bertrand Pluyaud
Classification JEL : C22, C52, C53, E37.
Keywords : GDP nowcasting; Real-time data; Mixed-frequency data.
Updated on: 06/12/2018 11:00