Background
Timely economic data is vital for evidence-based decision-making, particularly in rapidly evolving economic environments. Traditional forecasting methods often rely on quarterly gross domestic product (GDP) data, which are released with significant time lags, limiting their usefulness for real-time policy formulation. In response to this challenge, mixed frequency models, particularly Mixed Data Sampling (MIDAS) regressions, Unrestricted MIDAS (U-MIDAS) and Mixed-Frequency Vector Autoregression (MF-VAR) have emerged as powerful tools for nowcasting GDP using high-frequency indicators. It is for this reason that MEFMI will conduct a workshop on Nowcasting GDP using Mixed Frequency Models. The workshop will equip participants with the technical skills required to construct and apply nowcasting models based on mixed-frequency data. Participants will gain hands-on experience in implementing these models using EVIEWS, enabling them to produce more timely and reliable estimates of economic activity.

Objectives
This workshop aims to equip participants with practical skills in nowcasting GDP using high-frequency data. It covers the application of traditional bridge methods, MIDAS, and U-MIDAS models, along with forecast evaluation and interpretation techniques. Participants will also be introduced to Mixed-Frequency VAR and Bayesian VAR approaches using EVIEWS.

Content
The course will cover the following core topics:
• Introduction to High-Frequency Economic Indicators and Nowcasting Concepts.
• Bridge Models vs MIDAS Approaches.
• MIDAS and U-MIDAS Regression Models.
• Model Estimation and Forecast Evaluation Techniques.
• Mixed-Frequency Vector Autoregression (MF-VAR) and MF-BVAR; and
• Real-time nowcasting in EVIEWS.

Target Group
This course targets mid- to senior-level officials from central banks and ministries of finance who are engaged in macroeconomic modelling and analysis. A working knowledge of time series analysis and econometrics, as well as prior experience using EVIEWS, is highly recommended.