All Rights Reserved
AccessEcon LLC 2006, 2008.
Powered by MinhViet JSC

 
Christian Pierdzioch
 
''A bootstrap test of the time-varying efficiency of German growth forecasts''
( 2023, Vol. 43 No.1 )
 
 
I use a bootstrap approach to re-examine the time-varying efficiency of growth forecasts for Germany. I argue that, given this small sample of forecasts, the bootstrap approach renders it possible to trace out with more precision than a standard full-sample forecast-efficiency-regression model whether forecasts were efficient at any given point in time. As an empirical application of the bootstrap approach, I present results for six-months-ahead and one-year-ahead growth forecasts published by three German economic research institutes during the sample period 1970$-$2018. The results illustrate that the bootstrap approach, for various configurations of the forecast-efficiency-regression model, yields stronger evidence against forecast efficiency than a conventional full-sample model.
 
 
Keywords: Forecast efficiency; Bootstrap; Growth; Germany
JEL: E3 - Prices, Business Fluctuations, and Cycles: General (includes Measurement and Data)
C5 - Econometric Modeling: General
 
Manuscript Received : Oct 20 2022 Manuscript Accepted : Mar 30 2023

  This abstract has been downloaded 125 times                The Full PDF of this paper has been downloaded 156015 times