Abstract
Tests of asset-pricing models typically form portfolios of stocks (based on criteria such as market capitalization and book-to-market values). The validity of this approach has been debated (see, for example, Berk, Citation2000). We consider a simple method of testing asset-pricing models using the returns of individual securities and illustrate the approach in a test of the robustness of analyses reported by Durand et al. (Citation2006) and Limkriangkrai et al. (Citation2008).
This article has been adapted from research presented in Manapon Limkriangkrai's doctoral dissertation, and this article has benefited from incorporating comments made by the examiners: Philip Gray, Richard Heaney and Kwaku Opong from the PhD thesis examiners' reports. The authors accept full responsibility for any errors or omissions.
Notes
1We analyse the 124 individual securities that were listed continuously throughout the 1990–2001 period from the data set used both by Durand et al. (Citation2006) and Limkriangkrai et al. (Citation2008).
2To be consistent with Durand et al. (Citation2006) and Limkriangkrai et al. (Citation2008), we include January and July dummies.
3Turnover is generally defined as the number of shares traded divided by the number of shares outstanding (Datar et al., Citation1998).