Modelling the Pension Funds in Ghana Using Generalized Linear Model: A Case Study of Social Security and National Insurance Trust (SSNIT).

Thumbnail Image
November, 2016
Journal Title
Journal ISSN
Volume Title
In recent times some doubts have been expressed on the ability of the Social Security and National Insurance Trust (SSNIT) scheme to pay pensions in the future because its investments have yielded low returns. This calls for the reason to model the size of the pension fund in terms of the Investment Income, In ation rate, Contribution and Contributors. Generalised linear models, Gamma and Gaussian distributions were used to model the size of the pension fund using data from 1967 to 2013. The empirical results based on the Akaike Information Criteria (AIC), graphical analysis of QQ-Plots and plots of Residuals versus Fitted reveals that the Gamma regression is the best model as compared to the Gaussian regression model.
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 in Actuarial Science