The determinants of severe food insecurity in Africa using the longitudinal generalized Poisson mixed model

Abstract

Food insecurity is a multifaceted issue (challenge) that affects health care, policies, agriculture output leadership, the environment, the food system, and the politics of global commerce in the food industry. Our aim was to get the relevant components of food security and nutrition concerning Africa holistically and use these identified components to discover the most informative correlates that affect the number of severe food insecure individuals in Africa with its population as an offset. Principal Component Analysis (PCA) was used to detect the relevant components of Africa’s food security and nutrition. The Poisson Generalized Linear Mixed Model (GLMM) was employed to identify the significant components. Generalized estimating equations were then applied to account for the overdispersion associated with the Poisson distribution. To make the interpretation of the results more meaningful, 10 PCA components were selected. They explained 74.6\% of the variation within the data. The GLMM analysis remarkably identified Nutrient Intake, Average Food Supplied, Child Care, Dietary Supply Adequacy, and Feeding Practices Among Infants to be significantly associated with the Rate of Severe Food Insecure Individuals (p-value < 0.05). A better improvement in the average food supply in Africa is likely to yield an improvement in food security and nutrition. Our findings provide insight concerning Africa which will help policymakers create targeted plans for Africa that will address issues with food security and nutrition, and this will fuel the achievement of Sustainable Development Goal 2.

Keywords

• principal component analysis
• Poisson generalized linear mixed model
• food security
• nutrition