A new hybrid framework to monitor business cycle: the RAT-Ita approach

The aim of this paper is to introduce a new business cycle indicator that exploits a large information set (1,285 time series) to nowcast the GDP evolution in real time. The proposed indicator, called RAT(ing)-Ita, focusses on the binary event represented by the sign of the one-step-ahead GDP growth rate. In other terms, we use many monthly indicators to “rate” the next-period economic performance represented by the GDP direction of change. The proposed methodology is organised along three steps: selection of the indicators, prediction of the GDP sign based on the single time series and aggregation of the single signal. The first step relies on the joint use of Directional Accuracy Change test, Receiver Operating Characteristic and spectral coherence. In the second step, the probability of the event sign of the GDP change, delivered by each selected indicator, is accomplished by using either bivariate logit models or the binary point prediction based on the ROC. Finally, in the aggregation step we adopt alternative weighting schemes. The performance of the methodology has been tested by predicting the Italian GDP quarter-on-quarter directional changes in pseudo-real time from Q1-2014 up to Q3-2022. The results are compared with the traditional benchmark models used to forecast the GDP,showing a better performance of RAT-Ita.