Abstract:
In this paper we present a methodology which can help to improve the assessment of the current economic situation. We propose an approach which combines multivariate single equations to forecast the monthly growth rate of industrial production with a density forecast. This allows to estimate the current recession probability. In the analysis the focus is on the real-time problem, i.e. the fact that the reference series (industrial production) as well as important indicators are not available on a timely basis and are often revised substantially over an extended period. For this reason the whole analysis is carried out under real-time conditions. Indeed the forecast of the recession probabilities allows to identify the recession well before it can be seen in the official data. This result is encouraging. But there is still a substantial need for further research.