DSpace
 

KNUSTSpace >
Theses / Dissertations >
College of Science >

Please use this identifier to cite or link to this item: http://hdl.handle.net/123456789/6657

Title: Granger-Causality analysis of Ghana Universities Staff Superannuation Scheme (GUSSS), KNUST
Authors: Owusu, Boakye Robert
Issue Date: 29-Oct-2014
Abstract: The Ghana Universities Sta Superannuation Scheme (GUSSS) like any other pension scheme has income and expenditure patterns. However, whether in ows Granger-cause out ows or out ows Granger-cause in ows is unknown. This study investigates the state of the scheme, stability and long-term behaviors of the scheme, analyze the Granger-causality of in ows and out ows of funds and struc-ture of the scheme. In line with this objectives, secondary data of monthly in ows and out ows of funds for the period 2003 to 2009 were collected. The data was tted to vector autoregressive (VAR) model of order one(1) and the model param-eters were estimated by ordinary least squares(OLS) methods. It was found that the model variables were stationary after rst di erencing. The system matrix was also found the be stable. The Granger-causality test showed that out ows Granger-cause in ows which means that out ows of funds in the previous month has in uence on the in ows of funds in the current month. Again, the impulse response analysis showed that when one standard deviation shock was put to the error term, the model variables initially uctuated around the zero mean but remained steady and positive in the long-run. We therefore recommend that optimal investment portfolios must be adopted.
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 Master of Science Industrial Mathematics College of Science/Institute of Distance Learning, 2014
URI: http://hdl.handle.net/123456789/6657
Appears in Collections:College of Science

Files in This Item:

File Description SizeFormat
Robert Owusu Boakye.pdf532.79 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