This paper argues that probability forecasts convey information on the uncertainties that surround macro-economic forecasts in a straightforward manner which is preferable to other alternatives, including the use of confidence intervals. Probability forecasts obtained using a small benchmark macroeconometric model as well as a number of other alternatives are presented and evaluated using recursive forecasts generated over the period 1999q1-2001q1. Out of sample probability forecasts of inflation and output growth are also provided over the period 2001q2-2003q1, and their implications discussed in relation to the Bank of England’s inflation target and the need to avoid recessions, both as separate events and jointly. The robustness of the results to parameter and model uncertainties is also investigated by a pragmatic implementation of the Bayesian model averaging approach.

1. To estimate a small quarterly macroeconomic model of the UK, based on a VAR model of a number of ‘core ’ macroeconomic variables, and employing recently developed econometric techniques to test and impose restrictions on the long run relationships of the model. Also, to analyse the short run dynamic properties of the model and to investigate the role of exogenous variables, all with a view to analysing specific aspects of the way in which the UK macroeconomy functions. 2. To evaluate a limited number of economic theories within the context of a small but complete macromodel. 3. To construct a monthly model of the UK economy corresponding as far as possible to the quarterly model. 4. To undertake some policy evaluation exercises, and to investigate the sources of shocks which generate fluctuations in real and nominal macro-variables in the UK economy and the mechanisms by which the effects of different shocks are propagated across different macroeconomic variables and over time. Significant achievements