Have economic models' forecasting performance for US output growth and inflation changed over time, and when?

We evaluate various economic models' relative performance in forecasting future US output growth and inflation on a monthly basis. Our approach takes into account the possibility that the models' relative performance can vary over time. We show that the models' relative performance have, in fact, changed dramatically over time, for both revised and real-time data, and investigate possible factors that might explain such changes. In addition, this paper establishes two empirical stylized facts. Specifically, most predictors for output growth lost their predictive ability in the mid-1970s, and became essentially useless over the last two decades. When forecasting inflation, on the other hand, fewer predictors are significant, and their predictive ability worsened significantly around the time of the Great Moderation.