Measuring Yields: Arithmetic, Geometric and Horizon-Consistent Average

Michal Dvořák

Prague Economic Papers, 2016, vol. 2016, issue 3, 335-353

Abstract: The choice of averaging method has considerable impact on the average yield of a financial variable. Usually, geometric average is preferred, though dissenting opinions exist. Here it is shown that the problem has a consistent solution, which is called the horizon-consistent average. It is shown why geometric and arithmetic average calculations are almost always biased. When using company valuation's most common SP500 dataset by Ibbotson Associates for 1928-2012 and the recommended 10-year forecasting horizon, consistent with the 10-year government securities in a CAPM model, the arithmetic average is severely flawed. On the other hand, the geometric average for similar horizons does not deviate much from the horizon-consistent average.

Keywords: yield; risk premium; historical yield; geometric average; arithmetic average (search for similar items in EconPapers)
JEL-codes: G1 G32 (search for similar items in EconPapers)
Date: 2016
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://pep.vse.cz/doi/10.18267/j.pep.563.html (text/html)
http://pep.vse.cz/doi/10.18267/j.pep.563.pdf (application/pdf)
free of charge

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:prg:jnlpep:v:2016:y:2016:i:3:id:563:p:335-353

Ordering information: This journal article can be ordered from
Editorial office Prague Economic Papers, University of Economics, nám. W. Churchilla 4, 130 67 Praha 3, Czech Republic
http://pep.vse.cz

DOI: 10.18267/j.pep.563

Access Statistics for this article

Prague Economic Papers is currently edited by Klára Pavlová

More articles in Prague Economic Papers from Prague University of Economics and Business Contact information at EDIRC.
Bibliographic data for series maintained by Stanislav Vojir ().