Forecasting Private Consumption by Consumer Surveys


Konstantin Arkadievich Kholodilin, DIW, Berlin, Germany. E-mail:


Survey-based indicators are widely seen as leading indicators for economic activity. As such, consumer confidence might be informative for the future path of private consumption. Although the indicators receive high attention in the media, their forecasting power often appears to be very limited. This paper takes a fresh look at the data that serve as a basis for the consumer confidence indicator (CCI) reported by the EU Commission for the euro area. Different pooling methods are applied to exploit the survey information. Forecasts are based on mixed data sampling (MIDAS) and bridge equations. While the CCI does not outperform the autoregressive benchmark, the new indicators are able to raise forecasting performance. The best performing indicator should be built upon pre-selection methods. Data-driven aggregation methods should be preferred to determine the weights of the individual ingredients. Copyright © 2011 John Wiley & Sons, Ltd.