The Effects of Household Income and Food Expenditure on the Malaysian Household Food Security Index Using the Regularized 2SLS Regression

Nurul Najiha Abdul Rahman Adrin; Khuneswari Gopal Pillay

doi:10.48084/etasr.18054

Authors

Nurul Najiha Abdul Rahman Adrin Department of Mathematics and Statistics, Faculty of Applied Science and Technology, University Tun Hussein Onn Malaysia, Campus Pagoh, Muar, Johor, Malaysia
Khuneswari Gopal Pillay Department of Mathematics and Statistics, Faculty of Applied Science and Technology, University Tun Hussein Onn Malaysia, Campus Pagoh, Muar, Johor, Malaysia https://orcid.org/0000-0001-9111-0931

Volume: 16 | Issue: 4 | Pages: 37590-37598 | August 2026 | https://doi.org/10.48084/etasr.18054

Received: 9 February 2026 | Revised: 14 May 2026 | Accepted: 20 May 2026 | Online: 17 June 2026

Corresponding author: Khuneswari Gopal Pillay

Abstract

Household food security remains a critical concern in many Asian countries, including Malaysia, where disparities in income distribution and rising living costs continue to affect food access and stability. While existing studies primarily emphasize food security at the national level, empirical evidence at the household level remains limited. This study examines the effects of household income and food expenditure on the Household Food Security Index (HFSI) in Malaysia using a regularized Two-Stage Least Squares (2SLS) regression framework. By integrating Least Absolute Shrinkage and Selection Operator (LASSO) and Elastic Net techniques into the 2SLS estimation, the proposed approach addresses endogeneity and multicollinearity while enabling robust variable selection. Cross-sectional household data obtained from the Department of Statistics Malaysia (DOSM) for 2022 are utilized. The results indicate that the 2SLS-LASSO specification outperforms the Elastic Net model in terms of Akaike Information Criterion (AIC), Corrected Akaike Information Criterion (AICc), and Bayesian Information Criterion (BIC), providing a more parsimonious and interpretable model. Empirical findings reveal that higher household income, educational attainment, and employment stability are positively associated with food security, whereas income inequality (measured by the Gini coefficient) exerts a significant negative effect. Larger household size is associated with reduced per capita food security, reflecting resource constraints within households. This study contributes to the literature in two key ways: (i) by introducing a regularized 2SLS framework for analyzing household food security, and (ii) by proposing a structured and replicable formulation of the HFSI. The findings provide policy-relevant insights for addressing income inequality and improving targeted interventions for vulnerable households in Malaysia.

Keywords:

household food security, household income, household food expenditure, Two-Stage Least Squares (2SLS), regularization regression, LASSO, Elastic Net

References

[1] G. Makombe, "The food security concept: Definition, conceptual frameworks, measurement, and operationalization," Africa Development, vol. 48, no. 4, pp. 53–80, May 2024.

[2] FAO, IFAD, UNICEF, WFP, and WHO, The State of Food Security and Nutrition in the World 2025. Addressing high food price inflation for food security and nutrition. Rome, Italy: FAO; IFAD; UNICEF; WFP; WHO, 2025.

[3] Martin. "Goal 2: Zero Hunger." United Nations Sustainable Development. https://www.un.org/sustainabledevelopment/hunger/.

[4] I. Manikas, B. M. Ali, and B. Sundarakani, "A systematic literature review of indicators measuring food security," Agriculture & Food Security, vol. 12, no. 1, May 2023, Art. no. 10.

[5] K. Sajwan and S. P. Singh, "Multidimensionality of Household Food Security: A Systematic Review," Current Nutrition Reports, vol. 14, no. 1, Dec. 2025, Art. no. 127.

[6] Y. H. Abdi et al., "Regional disparities and sociodemographic determinants of food insecurity in Somalia: a secondary cross-sectional analysis of a National survey," Journal of Health, Population and Nutrition, vol. 44, no. 1, Oct. 2025, Art. no. 353.

[7] A. Sheikhi, F. Bahador, and M. Arashi, "On a generalization of the test of endogeneity in a two stage least squares estimation," Journal of Applied Statistics, vol. 49, no. 3, pp. 709–721, Feb. 2022.

[8] C. Chen, M. Ren, M. Zhang, and D. Zhang, "A Two-Stage Penalized Least Squares Method for Constructing Large Systems of Structural Equations," Journal of Machine Learning Research, vol. 19, Aug. 2018, Art. no. 2.

[9] Z. Sanioğlu-Tanış, D. Dündar-Öztaşçı, and İ. Özmen, "Fertility and women unemployment: new evidence from Türkiye," Economic Change and Restructuring, vol. 58, no. 6, Oct. 2025, Art. no. 89.

[10] M. Olmez Turan, B. Gilbert, and T. Flamand, "How good are weather shocks for identifying energy elasticities? A LASSO-IV approach to European natural gas demand," Journal of Commodity Markets, vol. 39, Sept. 2025, Art. no. 100498.

[11] O. M. Caccavale and V. Giuffrida, "The Proteus composite index: Towards a better metric for global food security," World Development, vol. 126, Feb. 2020, Art. no. 104709.

[12] G. Y. V. Tang, K. G. Pillay, and A. Mustapha, "The Impact of Data Preprocessing Order on LASSO and Elastic Net Capabilities," Engineering, Technology & Applied Science Research, vol. 15, no. 1, pp. 20264–20270, Feb. 2025.

[13] H. M. Nayem, S. Aziz, and B. M. G. Kibria, "Comparison among Ordinary Least Squares, Ridge, Lasso, and Elastic Net Estimators in the Presence of Outliers: Simulation and Application," International Journal of Statistical Sciences, vol. 24, no. 20, pp. 25–48, Dec. 2024.

[14] V. Tummalapalli, "Outlier Detection & Treatment for Machine Learning Models," International Journal of Innovative Research and Creative Technology, vol. 11, no. 3, pp. 1–8, June 2025.

[15] F. Belotti, G. Mancini, and G. Vecchi, "Outlier Detection for Welfare Analysis," World Bank, Washington, DC, USA, Policy Research Working Paper 10231, 2022.

[16] H. P. Vinutha, B. Poornima, and B. M. Sagar, "Detection of Outliers Using Interquartile Range Technique from Intrusion Dataset," in Proceedings of the 6th International Conference on Frontiers of Intelligent Computing: Theory and Applications, Bhubaneswar, India, 2017, pp. 511–518.

[17] T. Bennich, Å. Persson, R. Beaussart, C. Allen, and S. Malekpour, "Recurring patterns of SDG interlinkages and how they can advance the 2030 Agenda," One Earth, vol. 6, no. 11, pp. 1465–1476, Nov. 2023.

[18] S. Ullah, G. Zaefarian, and F. Ullah, "How to use instrumental variables in addressing endogeneity? A step-by-step procedure for non-specialists," Industrial Marketing Management, vol. 96, pp. A1–A6, July 2021.

[19] J. Fox and G. Monette, "Generalized Collinearity Diagnostics," Journal of the American Statistical Association, vol. 87, no. 417, pp. 178–183, Mar. 1992.

[20] B. Abdul-Hameed and O. G. Matanmi, "A Modified Breusch–Pagan Test for Detecting Heteroscedasticity in the Presence of Outliers," Pure and Applied Mathematics Journal, vol. 10, no. 6, pp. 139–149, Dec. 2021.

[21] R. Tibshirani, "Regression Shrinkage and Selection Via the Lasso," Journal of the Royal Statistical Society: Series B (Methodological), vol. 58, no. 1, pp. 267–288, Jan. 1996.

[22] H. Zou and T. Hastie, "Regularization and Variable Selection Via the Elastic Net," Journal of the Royal Statistical Society Series B: Statistical Methodology, vol. 67, no. 2, pp. 301–320, Apr. 2005.

[23] D. R. Bhandari, K. Shah, and A. Bhandari, "The Power of Outliers in Research: What actually Works, and Does it Matter?," Pravaha, vol. 30, no. 1, pp. 84–91, Dec. 2024.

[24] K. G. Pillay, F. M. San, R. M. Salleh, and A. Khamis, "LASSO regression to determine risk factors for road accident casualties in Malaysia in the presence of multicollinearity," AIP Conference Proceedings, vol. 2465, no. 1, June 2022, Art. no. 030001.

[25] Department of Statistics Malaysia. "Data Catalogue." OpenDOSM. https://open.dosm.gov.my.