Predicting the probability of a recession with nonlinear autoregressive leading-indicator models

We develop nonlinear leading-indicator models for GDP growth, with the inte rest-rate spread and growth in M2 as leading indicators. Since policy maker s typically are interested in whether a recession is imminent, we evaluate these models according to their ability to predict the probability of a rec ession. Using data for the United States, we find that conditional on the s pread, the marginal contribution of M2 growth in predicting recessions is n egligible.