Composite Survey Sentiment as a Predictor of Future Market Returns: Evidence for German Equity Indices

Zuzana Rakovska
Authors registered in the RePEc Author Service: Zuzana Gric

Working Papers from Czech National Bank, Research and Statistics Department

Abstract: In this paper, I construct a novel composite sentiment indicator which captures the irrational beliefs of the general population in Germany. This indicator is used to demonstrate that the sentiment of the general public is responsible for temporary overreactions of the aggregate German stock market and also of its narrower segments as embodied in four important equity indices from the DAX family. My results show that population-wide beliefs work as a contrarian predictor of future returns on German equity indices for horizons of six to twelve months. In addition, an out-of-sample framework is developed to underline the degree of improvement achieved by combining several survey-based measures into one composite sentiment indicator. The results reveal that the composite indicator exhibits more accurate forecasting performance than the popular sentiment measure, consumer confidence.

Keywords: Composite indicator; consumer confidence; DAX indices; return predictability; sentiment (search for similar items in EconPapers)
JEL-codes: G17 G40 G41 (search for similar items in EconPapers)
Date: 2020-12
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.cnb.cz/export/sites/cnb/en/economic-re ... wp/cnbwp_2020_13.pdf

Related works:
Journal Article: Composite survey sentiment as a predictor of future market returns: Evidence for German equity indices (2021)
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:cnb:wpaper:2020/13

Access Statistics for this paper

More papers in Working Papers from Czech National Bank, Research and Statistics Department Contact information at EDIRC.
Bibliographic data for series maintained by Tomas Karhanek ().