Box and Jenkins Arima Methodology on the Incidence of Malaria in Effiduase, Sekyere-East District
Malaria still remains a public health problem in Ghana despite marked reduction of cases in the last few years. To strengthen the country’s prevention and control measures, this study was carried out to develop forecasting and prediction models of malaria incidence in the endemic district of Ashanti Region using time series and ARIMA. This research is a study model of forecasting Malaria incidence of Effiduase in the Sekyere District. It provides us clues about the behaviour of the time series data and develops a statistical model that will aid in finding the future values of the disease for five-month period ahead. The paper examines stationary and nonstationary time series by differencing and forecasting. Two Box-Jenkins Autoregressive Integrated Moving Average (ARIMA) models are estimated over the period 2001-2010 for Malaria cases in Effiduase. The mean absolute percentage error (MAPE) and mean square error (MSE) are used as measures of forecast accuracy. As the best fitting ARIMA model is found to have the lowest MSE, it is used to obtain post-sample forecasts. The Model ARIMA (2, 1, 0) was identified and used to forecast the morbidity due to malaria for the period. The results show that if measures are not put in place to check the incidence of the disease, subsequent years will witness escalating results. Practically, I suggest that the use of insecticide treated mosquito nets in the system should be proportional to the level of the morbidity due to malaria at any time. Secondly, I recommend that efforts must be seriously made by the major players in the health sector to make the net readily available in the communities at low prices to enable the ordinary Ghanaian to purchase it.
A Thesis Submitted to the Department of Mathematics, Kwame Nkrumah University of Science and Technology, Kumasi in partial fulfilment of the requirement for the degree of Master of Science Mathematics Department, Institute of Distance Learning, 2011