Monetary policy in a Markov-switching vector error-correction model: Implications for the cost of disinflation and the price puzzle

Monetary policy vector autoregressions (VARs) typically presume stability of the long-run outcomes. We introduce the possibility of switches in the long-run equilibrium in a cointegrated VAR by allowing both the covariance matrix and weighting matrix in the error-correction term to switch. We find that monetary policy alternates between sustaining long-run growth and disinflationary regimes. Allowing state changes can also help explain the price puzzle and justify the use of commodity prices as a corrective measure. Finally, we show that regime-switching has implications for disinflationary monetary policy and can explain the variety of sacrifice ratio estimates that exist in the literature.