John C. Robertson

Overview

John C. Robertson is a senior economist in the macropolicy section at the Federal Reserve Bank of Atlanta. His applied research focuses on VAR-based macroeconomic forecasting, including the practical construction of monthly macro models, Chow-Lin temporal disaggregation of quarterly GDP, prior specification comparisons, and the conditional forecasting approach to staggered data release.

Key Contributions

• BVAR forecasting guide (Robertson-Tallman 1999): practitioner's reference for constructing and comparing monthly BVAR models; documents that Modified Litterman (adding $\lambda_5$ sum-of-coefficients and $\lambda_6$ cointegration dummy restrictions) achieves essentially the same RMSE as the full Sims-Zha prior; establishes that the long-run restrictions — not the systemwide Normal-Wishart covariance structure — drive ZVAR's forecast advantage over base Litterman.
• Conditional forecasting (Robertson-Tallman 1999): exposition of the Waggoner-Zha (1999) minimum-MSE conditional forecasting procedure and its application to the staggered GDP data release problem.

Related

• Ellis W. Tallman
• Minnesota Prior
• Conditional Forecasting
• Vector Autoregression
• Sims-Zha Prior
• Daniel Waggoner
• Tao Zha