Multiple Regimes in U.S. Monetary Policy? A Nonparametric Approach

We use nonparametric, local regression and regression tree analysis to assess whether there exist multiple regimes in U.S. monetary policy over the period 1955:3-2000:2. We model U.S. monetary policy using a Taylor rule specification for the nominal interest rate target. By contrast with standard parametric tests for regime changes, the nonparametric methods we use allow the data to determine the dimensions on which to split the sample for purposes of estimating the coefficients of the Taylor rule. We also develop a procedure to assess the statistical significance of these splits in contrast to earlier applications of these techniques. Our findings suggest that there are indeed multiple regimes in U.S. monetary policy over the period examined. Furthermore, these regimes not exclusively characterized by periods of time, but may also depend on certain threshold values for inflation and the output gap. These findings yield further insights on the conduct of monetary policy over the period examined.