Real Time Representation of the UK Output Gap in the Presence of Trend Uncertainty

This paper describes an approach that accommodates in a coherent way three types of uncertainty when measuring the output gap. These are trend uncertainty (associated with the choice of model and de-trending technique), estimation uncertainty (with a given model) and data uncertainty (associated with the reliability of data). The approach employs VAR models to explain real time measures and realisations of output series jointly along with Bayesian-style ‘model averaging’ procedures. Probability forecasts provide a comprehensive representation of the output gap and the associated uncertainties in real time. The approach is illustrated using a real time dataset for the UK over 1961q2 — 2005q4.