KNUSTSpace >
Theses / Dissertations >
College of Science >

Please use this identifier to cite or link to this item: http://hdl.handle.net/123456789/10047

Title: Modelling Volatility and the Risk-return Relationship of Selected Equities on the Ghana Stock Exchange
Authors: Abonongo, John
Issue Date: 20-Jan-2017
Abstract: The volatility and the risk-return trade o of equities or stock markets play essential role in investment, decision making, fi nancial stability among others. This study used secondary data of 35 equities from the Ghana Stock Exchange (GSE) and Annual Report Ghana databases comprising the daily closing prices from the period 02/01/2004 to 16/01/2015. Principal component analysis was used in selecting equities that characterized each sector. The results revealed that, for the Finance sector, CAL, ETI and GCB were selected, the Distribution sector had PBC and TOTAL selected, the Food and Beverage sector had FML selected, the Information Communication Technology sector had CLYD selected, the Insurance sector had EGL selected, the Manufacturing and Mining sectors had PZC, UNIL and TLW, AGA selected respectively. The symmetry and asymmetry of the daily returns of the selected equities as well as the risk-return relationship was investigated using the univariate GARCH-M (1, 1), EGARCH-M (1, 1) and TGARCH-M (1, 1) models and the results indicated the existence of positive risk premium meaning investors were compensated for holding risky assets. The results also showed that, the asymmetry models gave a better t than the symmetry model indicating the presence of leverage e ect among the selected equities. TGARCH-M (1, 1) model with the student-t distribution was the appropriate model selected. It was revealed that, volatility was persistent (explosive process) in most of the selected equities with the three distributional assumptions. The persistence in volatility was extended in investigating the half-life measure of the selected equities. It was revealed that most of the equities had strong mean reversion and short half-life measure. The long-run trends in volatility was investigated by regressing the conditional variance against a time variable. The results showed that, most of the equities exhibited increasing volatility over the sample period.
Description: A thesis submitted to the Department of Mathematics,Kwame Nkrumah University of Science and Technology in partial fulfillment of the requirement for the Degree of M.Phil Actuarial Science, 2016
URI: http://hdl.handle.net/123456789/10047
Appears in Collections:College of Science

Files in This Item:

File Description SizeFormat
John Abonongo.pdf618.7 kBAdobe PDFView/Open

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.


Valid XHTML 1.0! DSpace Software Copyright © 2002-2010  Duraspace - Feedback