Stochastic Modeling of Food Insecurity

Wang, Dieter ; Andree, Bo Pieter Johannes ; Chamorro, Andres Fernando ; Girouard Spencer, Phoebe

World Bank, Washington, DC

关键词: FOOD SECURITY;    FOOD INSECURITY;    FAMINE RISK;    VARIABLE SELECTION;    STOCHASTIC SIMULATION;   

DOI  :  10.1596/1813-9450-9413
RP-ID  :  WPS9413

学科分类：社会科学、人文和艺术（综合）

来源: World Bank Open Knowledge Repository

【 摘 要 】

Recent advances in food insecurityclassification have made analytical approaches to predictand inform response to food crises possible. This paperdevelops a predictive, statistical framework to identifydrivers of food insecurity risk with simulation capabilitiesfor scenario analyses, risk assessment and forecastingpurposes. It utilizes a panel vector-autoregression to modelfood insecurity distributions of 15 Sub-Saharan Africancountries between October 2009 and February 2019.Statistical variable selection methods are employed toidentify the most important agronomic, weather, conflict andeconomic variables. The paper finds that food insecuritydynamics are asymmetric and past-dependent, with lowinsecurity states more likely to transition to highinsecurity states than vice versa. Conflict variables aremore relevant for dynamics in highly critical stages, whileagronomic and weather variables are more important for lesscritical states. Food prices are predictive for all cases. ABayesian extension is introduced to incorporate expertopinions through the use of priors, which lead tosignificant improvements in model performance.