Investigating the structure of expansions and recessions in US business cycle: a modified recursive partitioning approach

In this paper the problem of identifying the structure of expansions and recessions in the US economy is placed in the framework of recursive partitioning and discriminant analysis. The classification provided by the National Bureau ofEconomic Research (NBER) is considered. Using as covariates themain variables and indicators deemed useful to predict the business cycle, a modified recursive partitioning approach isproposed at each step (tree node) the method identifies the linear combination of the covariates that discriminates the mostbetween being in and out of a recession this new covariate is then used to split the data. The application to the case of the US business cycle and the comparison with classical logisticregression shows the merits of the proposed approach that represents a useful to tool to identify and to interpret thestructure of expansionsand recessions.