Socioeconomic factors affecting food security in Uganda were studied in 2004-2005, and secondary agricultural production data collected by the Uganda Bureau of Statistics used to determine famine-prone households. The relationship between predictor and outcome variables was determined using a logistic regression model. Famine risk at different strata of predictive variables was analyzed using bivariate analysis. The model was fitted with 13 factors, with those significantly related to food insecurity found to be distance to gardens, household size, amount of labor input, livestock number, distance to main roads, household income, household head age, and agricultural shock. Further study using a predictive model combining environmental stress and socioeconomic factors would improve food insecurity prediction.