Nowcasting and Short-term Forecasting of Chinese Quarterly GDP: Mixed Frequency Approach

Abstract

Conventional macroeconomic forecasting model must change the mixed frequency data into the same frequency data by means of aggregation and interpolation, which ignores the information of high frequency data and decreases the timeliness and accuracy of nowcasting and short-term forecasting. Using monthly and quarterly macroeconomic data, this paper apply mixed data sampling (MIDAS) model and mixed-frequency VAR model (MF-VAR) to nowcast and forecast Chinese quarterly GDP growth rate. The results show that MIDAS model considering an autoregressive item tends to perform better in shorter horizons, whereas MF-VAR model in longer horizons. Additionally, the pooled forecast of MIDAS model and MF-VAR model outperform the individual models. Finally, forecasting results reveal that China's quarterly GDP growth will rebound steadily from the beginning of the third quarter of 2012