Combining principal component analysis and logistic regression models to assess household level food security among smallholder cash crop producers in Kenya

摘要

Concerns about rising food insecurity in developing countries have prompted a lot of research. This paper deals with household survey of cash crop smallholders in Murang'a District, Kenya. The paper focuses on how factors related to cash crops production affect food security. Principal component analysis was applied in developing a relative food security index that was used as an outcome variable in logistic regression to predict factors affecting food security in this region. Results indicate that the percentage of food secure households is lower in the tea zone. This is despite relatively higher income from tea production. Income from tea is used in food purchase because of insignificant own production. Coffee farmers concentrate more in food thancoffee production. They may therefore produce adequate for their households and sell any surplus. Further results indicate that increasing land under cash crop would increase the likelihood of a household being food insecure.