Accurate economic forecasting and robust structural modeling are the indispensable foundations for effective central bank decision-making, particularly in monetary policy. This course is designed to provide a comprehensive, hands-on understanding of the state-of-the-art techniques central banks use to project key macroeconomic variables like inflation, GDP, and interest rates. Participants will engage with various modeling frameworks, from simple Time Series models to complex Dynamic Stochastic General Equilibrium (**DSGE**) models, and learn the practical challenges of integrating judgment and real-time data into the forecasting process. The goal is to produce skilled practitioners capable of generating policy-relevant forecasts and scenario analyses.
Forecasting and Economic Modeling for Central Banks
Central Banking and Monetary Policy
November 30, 2025
Introduction
Objectives
Upon completion of this program, participants will be able to:
- Evaluate the strengths and weaknesses of different economic modeling frameworks used by central banks.
- Apply and interpret various Time Series (e.g., VAR, BVAR) and semi-structural models for forecasting.
- Understand the conceptual foundations and policy uses of **Dynamic Stochastic General Equilibrium (DSGE)** models.
- Conduct scenario and shock analysis using established central bank models.
- Incorporate nowcasting techniques and high-frequency data into the short-term forecast process.
- Critically assess forecast accuracy using relevant metrics and identify sources of forecast error.
- Apply judgment and qualitative information to adjust model-based forecasts effectively.
- Communicate model assumptions, results, and uncertainties clearly to policy makers.
Target Audience
- Central Bank Economists and Forecasting Analysts
- Government Economic Policy Advisors and Modellers
- Researchers and Academics in Applied Macroeconomics
- Financial Market Strategists and Investment Bank Economists
- Analysts responsible for internal corporate economic planning
- Advanced students in Quantitative Economics or Finance
Methodology
Hands-on modeling exercises (Matlab/Dynare, R/Python), Forecasting competition using real-time data, Policy shock simulation workshops, Group project on DSGE model interpretation, Discussions on judgmental adjustment techniques, Presentation skills for communicating technical results.
Personal Impact
- Acquire highly specialized skills in central bank-level economic modeling and forecasting.
- Master the practical application of VAR, BVAR, and DSGE models.
- Enhance analytical skills for data-driven policy recommendations.
- Improve ability to assess and manage model risk and forecast uncertainty.
- Gain proficiency in using real-time data and nowcasting techniques.
- Advance career in economic research, policy analysis, and quantitative finance.
Organizational Impact
- Improve the accuracy, transparency, and rigor of the organization's economic forecasts.
- Enhance the credibility of policy decisions through robust, evidence-based modeling.
- Facilitate better communication of economic outlook and policy rationale to the public.
- Strengthen internal capacity for conducting sophisticated scenario and stress testing.
- Ensure compliance with best practices in model governance and validation.
- Better inform strategic planning and risk management across departments.
Course Outline
Unit 1: The Central Bank Forecasting Process
Section 1: Objectives and Data Integration- The role of the forecast in the monetary policy cycle and policy communication.
- The "data triangle": nowcasting, short-term projection, and medium-term model-based forecast.
- Data sources: official statistics, high-frequency data, surveys, and alternative data.
- Techniques for seasonal adjustment, data smoothing, and handling revisions.
- Introduction to Univariate and Multivariate Time Series models (ARIMA, VAR).
- The use of Bayesian Vector Autoregression (BVAR) models for high-dimensional data.
- The methodology of the **"judgmental overlay"** and its governance.
- Combining forecasts: ensemble methods and weighting schemes.
Unit 2: Macroeconomic Modeling Frameworks
Section 1: Semi-Structural Models- Key equations and structure of the New Keynesian (NK) IS-LM-PC model.
- Estimation and calibration of semi-structural models for domestic and open economies.
- Using semi-structural models for policy impulse response analysis.
- Advantages and limitations relative to full structural models.
- The conceptual foundations and micro-foundations of DSGE models.
- Calibration vs. Bayesian estimation of DSGE models.
- Using DSGE models for counterfactual analysis and shock identification.
- Challenges in DSGE model complexity, parameter identification, and communication.
Unit 3: Scenario Analysis and Nowcasting
Section 1: Scenario and Shock Analysis- Designing policy-relevant alternative scenarios (e.g., supply shock, financial crisis).
- Simulating the impact of exogenous shocks on model variables.
- Conducting variance decomposition and historical shock analysis.
- Utilizing models for stress testing the economy and financial system.
- Techniques for nowcasting GDP and inflation (e.g., factor models, bridge equations).
- Incorporating high-frequency data (e.g., Google Trends, card transactions) into short-term projections.
- Machine learning techniques for feature selection in nowcasting.
- Managing the "fog of the present" through real-time data monitoring.
Unit 4: Model Governance and Communication
Section 1: Forecast Evaluation and Governance- Metrics for evaluating forecast accuracy (e.g., RMSE, MAE, Theil's U).
- Conducting **forecast error decomposition** and identifying sources of error.
- Model risk management and the independent validation process.
- Documenting model assumptions, limitations, and data dependencies.
Ready to Learn More?
Have questions about this course? Get in touch with our training consultants.
Submit Your Enquiry