Parametric and Nonparametric Estimation of Conditional Return Expectations

Wolfgang Drobetz and Daniel Hoechle ()
Additional contact information
Daniel Hoechle: University of Basel

A chapter in Risk Management, 2005, pp 169-196 from Springer

Abstract: Abstract This paper explores different specifications of conditional return expectations. We compare the most common specification, linear least squares, with nonparametric techniques. Our results indicate that nonparametric regressions capture some nonlinearities in financial data. In-sample forecasts of international stock market returns are improved with nonparametric techniques. However, there is very little out-of-sample prediction power for both linear and nonparametric specifications of conditional expectations. If an asset manager relies on a simple instrumental variable regression framework to forecast stock returns, our results suggest that linear conditional return expectations are a reasonable approximation.

Keywords: Conditional Expectation; Predictability; Linear Least Squares; Nonparametric Regression (search for similar items in EconPapers)
Date: 2005
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
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:spr:sprchp:978-3-540-26993-9_9

Ordering information: This item can be ordered from
http://www.springer.com/9783540269939

DOI: 10.1007/3-540-26993-2_9

Access Statistics for this chapter

More chapters in Springer Books from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().