Mathematics, Statistics and Actuarial Science

Permanent URI for this collection

https://erepository.mku.ac.ke/handle/123456789/172

Browse

Recent Submissions

Now showing 1 - 2 of 2
  • Thumbnail Image
    PublicationOpen Access
    Garched investment decision making with real risk
    (International Journal of Business and Public Management, 2011) Anyika, Emma; Weke, Patrick; Achia, Thomas
    Actual future market risks (systematic or non-diversifiable) of investment portfolios are determined in this paper. Future returns are first forecasted using past returns and GARCH (General Autoregressive Conditional Heteroskedastic) models. A Real Risk Weighted Pricing Model (RRWPM) is used to estimate future systematic risk among other parameters and determines the future costs of the portfolios. Forecasted random error is then calculated as a random variable and used to determine probability density estimates of portfolios market risk. This enables future actual market risks of portfolio investments to be derived hence facilitating proper future investment decision making.
  • Thumbnail Image
    PublicationOpen Access
    Construction of Markov Transition Matrices for Cohorts of Students in Bsc.Actuarial Science Programme
    (Mount Kenya University, 2016) Imboga, O. Herbert; Orwa, George O.; Humpreys, H.M.
    This paper presents an application of Markov Analysis of student flow in a higher educational institution. In the education system not all students who begin an academic year stay till the end. Many of them invariably drop out for a variety of reasons. A transition model is one which describes the stocks and flows of students through an education system in terms of transition ratios. In this paper we describe one such model which traces the flow of a cohort of students through the system. In this study, the model considered is that of first-order Markov chain. Also the particular Markov chain studied here has a finite number of states and a finite number of points at which the observations are made. It is shown that under fairly general Markov chain model of the transitional determination, student flows do not display the random walk characteristics which may be interpreted as purely following a Markov process