A Times Series Analysis into the Rainfall Patterns in Four Selected Regions of Ghana

Loading...
Thumbnail Image
Date
2011
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
In recent times there have been calls on the climatic changes that are happening and the need to put measures in place to forestall drastic changes in the climate. In this study therefore, we attempted to study the trend of rainfall patterns in Ghana for four regions: Northern, Western, Eastern, and the Greater Accra Region, using four models namely: Linear Trend with Seasonal Terms, Seasonal Exponential Smoothing, ARIMA, Simple Exponential Smoothing, and Linear (Holt) Exponential Smoothing. All the ARIMA models are one model family, and the Simple Exponential Smoothing and Linear (Holt) Exponential Smoothing which is one model family, since the Simple Exponential Smoothing is just basics of the Linear (Holt) Exponential Smoothing. We have been able to show that the best model for the prediction of rainfall in the regions under study was Linear Trend with Seasonal Terms; in choosing this model we used the Means Square Error (MSE) and the R-Square as a criterion for the selection of the best model for prediction. We also further were able to come to the conclusion that the levels of rain in this four regions are not going to fall but rather will rise at least for the year 2011.
Description
A thesis submitted to the Board of Postgraduate Studies, Kwame Nkrumah University of Science and Technology, Kumasi, in partial fulfilment of the requirements for the award of the Degree of Master of Philosophy in Mathematics, 2011
Keywords
Citation