ASYMMETRIC PERSISTENCE IN GDP - A DEEPER LOOK AT DEPTH

If an economic time series behaves asymmetrically, then an interpretat ion of economic fluctuations based on linear time-series models could be misleading. Beaudry and Koop (1993) recently argued that for post-w ar US GDP data there exists a statistically significant difference in persistence between negative and positive shocks. We demonstrate that their test has two pitfalls: First, the t-statistic for testing asymme try in persistence does not have a conventional interpretation. Second , a highly significant I-value may come from sources different from as ymmetry. Using international data, we investigate for the presence of asymmetric persistence across the G-7 countries. (C) 1997 Elsevier Sci ence B.V. All rights reserved.