Comment on "Economic Forecasting in a Changing World" (by Michael Clements and David Hendry)

Michael Clements and David Hendry make realistic assumptions about the nature of the economy and the models used to forecast it. Under those assumptions, Clements and Hendry clarify why forecasting models work when they do, and why they don't work when they don't. Their research also suggests how to improve the forecasting abilities of existing models.A taxonomy of the sources of forecast error underpins Clements and Hendry's analysis. In my comments, I summarize their taxonomy; illustrate several implications, including for predictable and unpredictable forecast uncertainty; and re-examine forecast criteria, focusing on how mean square forecast errors can mislead.