This article evaluates the use of nancial data sampled at high frequencies to improve short-term forecasts of quarterly GDP for Mexico. The model uses both quarterly and daily sampling frequencies while remaining parsimonious. In particular, the mixed data sampling (MIDAS) regression model is employed to deal with the multi-frequency problem. To preserve parsimony, factor analysis and forecast combination techniques are used to summarize the infor- mation contained in a data set containing 392 daily nancial series. Our ndings suggest that the MIDAS model incorporating daily nancial data leads to improvements in quarterly forecasts of GDP growth over traditional models that either rely only on quarterly macroeconomic data or average daily frequency data. The evidence suggests that this methodology improves the forecasts for the Mexican GDP notwithstanding its higher volatility relative to that of developed countries. Furthermore, we explore the ability of the MIDAS model to provide forecast updates for GDP growth (nowcasting).

  • Link al documento
  • Autor(es): Esta dirección de correo electrónico está siendo protegida contra los robots de spam. Necesita tener JavaScript habilitado para poder verlo. - Esta dirección de correo electrónico está siendo protegida contra los robots de spam. Necesita tener JavaScript habilitado para poder verlo.
  • Fecha: 2017-04-01
  • Palabras Clave: GDP forecasting, mixed frequency data, daily nancial data, nowcasting
  • Código Jel: C22, C53, E37
  • Idioma: Inglés/English
  • Número de páginas: 31
  • Volumen: Volume 17 Number 2
  • Issue: Spring 2017
  • Páginas: 173-203
  • Esta dirección de correo electrónico está siendo protegida contra los robots de spam. Necesita tener JavaScript habilitado para poder verlo.