GDP Forecast Accuracy During Recessions

This paper proposes a simple nonlinear framework to produce real-time multi-horizon forecasts of economic activity as well as conditional forecasts that depend on whether the horizon of interest belongs to a recessionary episode or not. It is hence particularly well-suited for the actual (post-)pandemic crisis that the world is facing. Moreover, it can be applied easily to any country and measure of economic activity. The forecasting model takes the form of an autoregression that is augmented with either a probability of recession or an inverse Mills ratio. The method is applied to US data over the 1959-2016 sample. The most parsimonious augmented autoregressive model delivers more accurate out-of-sample forecasts of GDP growth than the linear and nonlinear benchmark models considered, and this is particularly true during recessions. Our approach suits particularly well for the real-time prediction of final releases of economic series before they become available to policy makers. Moreover, standard probit models are used to generate the Term Structure of recession probabilities. Interestingly, the dynamic patterns of these Term Structures are informative about the business cycle turning points.