A Comparative Analysis of Aggregational Gaussianity Across Different Market Capitalisations for JSE-listed Shares and Indices

Ryan Kruger, Chun-Sung Huang, Kanshukan Rajaratnam and Chun-Kai Huang ()
Additional contact information
Chun-Kai Huang: Curtin University

The African Finance Journal, 2019, vol. 21, issue 2, 24-35

Abstract: A topic of recent interest is whether returns on the Johannesburg Stock Exchange (JSE) exhibit Aggregational Gaussianity (AG). Moreover, whether there exists a link between market capitalisation of shares and the AG of its returns. In this paper, we examine index and share returns from the JSE for evidence of AG with a particular focus on whether the results differ between (a) index and share samples and (b) shares and indices of different sizes as defined by market capitalisation. Various normality tests are combined with a quasi-random resampling procedure to obviate endpoint, overlapping and sample size biases. Our findings suggest that the assumption of AG, even at higher lags, needs to be made with caution. This is demonstrated by the varying test results as we moved from the index level to the individual share level.

Keywords: Aggregational Gaussianity; Johannesburg Stock Exchange; Shapiro-Wilk; Anderson- Darling; Kolmogorov-Smirnov; quasi-random sampling (search for similar items in EconPapers)
JEL-codes: C12 C15 C46 G10 (search for similar items in EconPapers)
Date: 2019
References: Add references at CitEc
Citations:

Downloads: (external link)
https://journals.co.za/content/journal/10520/EJC-1b9cc85837?fromSearch=true (text/html)

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:afj:journl:v:21:y:2019:i:2:p:24-35

Access Statistics for this article

More articles in The African Finance Journal from Africagrowth Institute Contact information at EDIRC.
Bibliographic data for series maintained by Kirk De Doncker ().