MODELING KEY DETERMINANTS OF THE HOUSEHOLD FOOD SECURITY IN RWANDA: PROBIT REGRESSION APPROACH

Abstract: Rwanda runs the risk of slowing further progress toward the achievement of MDG-1 to eradicate extreme hunger and poverty. Thus there was needed to understand factors that influence and determine food security in Rwanda. A probit regression procedure was employed on household cross sectional data surveyed by WFP Comprehensive Food Security and Vulnerability Analysis and Nutrition Survey 2012 in a joint initiative between the Rwandan National Institute of Statistics and the Ministry of Agriculture and Animal Resources. The backward elimination and stepwise methods determined automatically which variables to keep or drop from the model. Of the seven variables fitted in the model; Sex of household head and Education level of household head as demographic determinants of household food security and Size of land, Access to nearest market, Livestock ownership and climatic adaptation as the economic determinants of household food security were found to be statistically significant. Marginal effects showed that households with education level of head of household and households owning livestock were more likely to be food secure than their counterparts. Correctly classified of 75.72% And the area under the receiver operating characteristic (ROC) curve of 0.71 indicated that the model was correctly specified. These results have policy implications for Food Security Status of Households in developing countries like Rwanda. Keywords: Probit, food security, Rwanda. Title: MODELING KEY DETERMINANTS OF THE HOUSEHOLD FOOD SECURITY IN RWANDA: PROBIT REGRESSION APPROACH Author: NDAKAZA Jean Napoleon, Dr. Joseph K. Mung’atu, Dr. NDENGO Marcel, HAGENIMANA Felix, GASHEJA Christophe, HARERIMANA jean de Dieu International Journal of Mathematics and Physical Sciences Research ISSN 2348-5736 (Online) Research Publish Journals

Citation