Time-varying risk components in the single-factor market model: an exact most powerful invariant test
Philip Shively
Applied Financial Economics, 2004, vol. 14, issue 13, 945-952
Abstract:
There is mounting evidence that stock prices have a time-varying predictable component. This paper tests for time-varying systematic risk, market compensation for systematic risk, and risk premiums in the single-factor market model to determine (1) whether the predictable stock-price component is due to time-varying risk premiums in an efficient market or an inefficient market with constant risk premiums, and (2) whether the time-varying risk premiums are due to time-varying systematic risk or time-varying market compensation for systematic risk. This paper applies an exact small-sample, pointwise most powerful invariant test to ten size and 12 industry portfolios. It finds consistent evidence of time variation in all three risk components over the full 35-year sample, but largely sporadic evidence of time variation over the five seven-year subsamples. Of the portfolios that show evidence of time-varying risk premiums, they are most likely the result of time-varying market compensation for systematic risk and not time-varying systematic risk.
Date: 2004
References: View references in EconPapers View complete reference list from CitEc
Citations:
Downloads: (external link)
http://www.tandfonline.com/doi/abs/10.1080/0960310042000180817 (text/html)
Access to full text is restricted to subscribers.
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:taf:apfiec:v:14:y:2004:i:13:p:945-952
Ordering information: This journal article can be ordered from
http://www.tandfonline.com/pricing/journal/RAFE20
DOI: 10.1080/0960310042000180817
Access Statistics for this article
Applied Financial Economics is currently edited by Anita Phillips
More articles in Applied Financial Economics from Taylor & Francis Journals
Bibliographic data for series maintained by Chris Longhurst ().