Original research (Published On: 25-Jun-2019)

Consequences of measurement error in food insecurity assessment using household expenditure

Gabriel Mwenjeri, Samuel Mwakubo and Bernard Njehia

J. Agri. Res. Adv., 01 (02):19-22

Gabriel Mwenjeri: Department of Agricultural Economics, Kenyatta University, Nairobi

Samuel Mwakubo: School of Business and Economics, Pwani University, Kenya

Bernard Njehia: Department of Agribusiness and Trade, Kenyatta University, Nairobi

Download PDF Here

Article History: Received on: 03-Apr-19, Accepted on: 17-Jun-19, Published on: 25-Jun-19

Corresponding Author: Gabriel Mwenjeri


Citation: Mwenjeri GW, Mwakubo S and Njehia B (2019). Consequences of measurement error in food insecurity assessment using household expenditure. J. Agri. Res. Adv., 01 (02):19-22


Aim: The objective of the experiment is to highlight the implication of measurement error in formulation of strategies for addressing food insecurity.

Method and Materials: Using random sampling techniques and employing Fishers formula a total of 323 households were selected for the study. Informed by Engel’s law of inverse relationship between total household expenditure and the expenditure share on food, plus adding a quadratic term in the equation, the study sort to estimate the magnitude of food insecurity in Mandera County. The study employed econometric models including ordinary least squares and using instrumental variable in generalized method of moment (GMM) techniques to quantitatively analyze data on quadratic Engel curve.

Results: In this study, measurement error reduced parameter reliability by 32% which led to underestimation of food insecurity by about 20%. The results demonstrated that microeconomic data are contaminated by measurement errors which reduce reliability of parameters.

Conclusion: Research concluded that household expenditure is not a perfect measure of the actual food insecurity situation. The fact that significant variance in total household expenditure is due to measurement error demonstrates the contamination ofmicroeconomic data.


Article View: 526
PDF Downloaded: 60