A bounded model of time variation in trend ination, NAIRU and the Phillips curve

Abstract: In this paper, we develop a bivariate unobserved compo-nents model for ination and unemployment. The unobserved components are trend ination and the non-accelerating ination rate of unemployment (NAIRU). Our model also incorporates a time-varying Phillips curve and time-varying ination persistence. What sets this paper apart from the ex-isting literature is that we do not use unbounded random walks for the un-observed components, but rather use bounded random walks. For instance, NAIRU is assumed to evolve within bounds. Our empirical work shows the importance of bounding. We \u85nd that our bounded bivariate model fore-casts better than many alternatives, including a version of our model with unbounded unobserved components. Our model also yields sensible estimates of trend ination, NAIRU, ination persistence and the slope of the Phillips curve