Fornari and Mele (2009) provide a detailed assessment of the out of sample forecasting ability of univariate linear and non linear models which rely on financial indicators. Overall, their conclusion is that the term spread, together with a time-varying measure of stock market volatility, does a rather good job in anticipating the rates of change in the US post-War industrial production index. However, nearly all of the combinations of variables they look at have their moment of popularity, so that what is eventually judged to be the best model is not the best model consistently across the sample. This finding cannot but confirm that recessions are.
