Multivariate Estimates of the Permanent Components in GNP and Stock Prices

Journal of Economic Dynamics and Control, 12 (June/July 1988) 255-296. (With Argia M. Sbordone). This paper sits halfway between the “random walk in GNP” JPE and “permanent and transitory components” QJE. The “random walk” is univariate. Here, we realized that consumption could tell you a lot about the permanent component of GNP. Here, we use that insight in spectral and variance-ratio calculations. The answers are the same as in “permanent and transitory components”, but I now prefer the simpler VAR treatment in that paper. When GNP or stock prices are cointegrated with a  random walk the subtle long-horizon and “nonparametric” techniques needed in the “random walk in GNP” really are no longer needed; short order models to produce good long-term forecasts.

Read More >

Previous
Previous

How Big is the Random Walk in GNP?