A model of the federal funds rate target

This paper is a statistical analysis of the manner in which the Federal Reserve determines the level of the federal funds rate target, one of the most publicized and anticipated economic indicators in the financial world. The paper introduces new statistical tools for forecasting a discrete-valued time series such as the target and suggests that these methods, in conjunction with a focus on the institutional details of how the target is determined, can significantly improve on standard vector autoregression forecasts of the effective federal funds rate. We further show that the news that the Fed has changed the target has statistical content substantially different from the news that the Fed failed to make an anticipated target change, causing us to challenge some of the conclusions drawn from standard linear VAR impulse-response functions.