Return prediction with time varying betas: a research in BIST

Ayca Akyatan and Mustafa Koray Cetin

International Journal of Accounting and Finance, 2020, vol. 10, issue 1, 64-86

Abstract: In the present study, dynamic versions of beta, which is the risk measure of investment instruments, have been employed to predict daily return of 30 random portfolios made of 154 stocks transacted in BIST ALL between dates 02.01.2003 and 29.08.2013. BIST 100 Index has been employed as the market portfolio. The predictions have been made with rolling regression and MGARCH methods. The performance of return predictions of dynamic betas has been compared to the performance of return predictions of traditional beta. Dynamic betas have been estimated with rolling regression, MGARCH DVECH, MGARCH DBEKK, MGARCH CCC and MGARCH DCC. In the study, it has been identified that the return prediction made with dynamic betas performed better than the predictions made with traditional beta. However, the return predictions made with CCC betas have been superior to other dynamic betas in terms of beating the performance of traditional beta.

Keywords: risk; return prediction; conditional covariance; rolling regression; MGARCH; dynamic beta; dynamic conditional correlation; DCC; constant conditional correlation; CCC; diagonal BEKK; DBEKK; BIST. (search for similar items in EconPapers)
Date: 2020
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.inderscience.com/link.php?id=111240 (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:ids:intjaf:v:10:y:2020:i:1:p:64-86

Access Statistics for this article

More articles in International Journal of Accounting and Finance from Inderscience Enterprises Ltd
Bibliographic data for series maintained by Sarah Parker ().