The implication of free primary education in Kenya:A stochastic model

Abstract

Markov models have in the past been applied in the development of manpower planning models and in education models. In this project, a maximum - likelihood based transition matrix is developed and then used to project the primary school enrolments for the year 2003, since there was an influx of pupils in the Primary education when the free primary education policy was enforced. The difference between the projected and the observed enrolments is obtained and is translated to be the number of new entrants into the system. The model developed is subsequently applied in obtaining a number of education characteristics such as the length of schooling, the cost of educating the new entrants, staff and capital requirements. Matlab (Version 6.1) is used to generate the fundamental matrix and the projections. From the model, the results indicates that there is a noticeable difference between the actual (observed) enrollments and the projected (expected) enrollment in the year 2003. This difference translates to some implications in the education system like the need for more teachers, more classes and increase in other capital requirements. The model is validated using year 2004 and 2005 observed enrollment data.