Working Paper
Log versus level in VAR forecasting: 16 Million empirical answers - expect the unexpected
Johannes Mayr, Dirk Ulbricht
ifo Institut für Wirtschaftsforschung, München, 2007
Ifo Working Paper No. 42
ifo Institut für Wirtschaftsforschung, München, 2007
Ifo Working Paper No. 42
The use of log-transformed data has become standard in macroeconomic forecasting with VAR models. However, its appropriateness in the context of out-of-sample forecasts has not yet been exposed to a thorough empirical investigation. With the aim of filling this void, a broad sample of VAR models is employed in a multi-country setup and approximately 16 Mio. pseudo-out-of-sample forecasts are evaluated. The results show that, on average, the knee-jerk transformation of the data is at best harmless.
JEL Classification: C520,C530