As the New Keynesian output gap cannot be observed, there is quite some debate on the question what this variable looks like. Rather than taking the standard approach of using a time trend or the HP-...lter to estimate it, this paper separates trend from cycle via Bayesian estimation of a New Keynesian model, augmented with an unobserved components model for output. This provides us with a model consistent estimate of the output gap. This estimate is compared to popular proxies used in the

more »

... ature. It turns out that the bene...ts of using the model-based approach mainly lie in real time.