In this paper, I assess the evidence for a structural break in labor productivity growth in the years before the Great Recession with the use of out-of-sample forecasting exercises for the years 2010 to 2019 and the recently developed Beveridge–Nelson filter. Models based on a Beveridge–Nelson filter with no structural breaks outperform those allowing for a structural break, and there is statistically significant evidence that they outperform the random walk, though all models were too optimistic about labor productivity growth. Recently developed statistical tests do point to the presence of a structural break before the Great Recession, but uncertainty about the data-generating process for labor productivity growth or the timing and magnitude of the break may be too great to be helpful in forecast preparation.

在本文中，我通过使用2010年至2019年的样本外预测活动以及最近开发的Beveridge-Nelson滤波器，评估了大萧条之前几年劳动生产率增长出现结构性中断的证据。基于Beveridge-Nelson滤波器且无结构性断裂的模型优于那些允许结构性断裂的模型，并且有统计学上的显着证据表明它们优于随机游走，尽管所有模型都对劳动生产率的增长过于乐观。最近开发的统计检验确实指出了大萧条之前存在结构性断裂的情况，但是劳动生产率增长的数据生成过程或断裂的时间和幅度的不确定性可能太大，以至于无法进行预测准备。