Modeling Adoption Behavior of Organic Agriculture in Shabestar County: Comparing Ordered Logit and Random Forest Approaches

Document Type : Research Paper

Authors

1 Department of Agricultural Economics, Faculty of Agriculture, University of Tabriz, Iran

2 Master of Science in Computer Architecture, Staff Member of the Faculty of Agriculture, University of Tabriz.

10.22034/saps.2025.66607.3356

Abstract

Background & Objective: Organic farming, as a sustainable approach to mitigating environmental impacts and enhancing ecosystem health, plays a pivotal role in sustainable development. This study aimed to analyze the factors influencing the adoption of various levels of organic farming practices among wheat and barley farmers in Shabestar County.
Materials & Methods: The study population comprised wheat and barley farmers in Shabestar County, from which 175 individuals were selected using simple random sampling in 2023. Data were collected through questionnaires and face-to-face interviews and analyzed using ordinal logit and random forest models.
Results: The ordinal logit model revealed that 51% of farmers adopted at least one organic practice. Awareness, education, and participation in extension training programs exhibited significant positive effects, while farmers’ age and experience showed significant negative effects. The random forest model, with 78% accuracy, confirmed awareness and education as the most influential positive factors. Both models indicated that 69% of farmers would adopt organic practices if guaranteed purchase mechanisms were available.
Conclusion: Targeted education and economic incentives are essential to enhance adoption. The random forest model performed better in predicting lower adoption levels, whereas the ordinal logit model provided more precise insights into causal relationships. It is recommended that extension programs focus on younger farmers and that markets for organic products be developed. Resistance from older farmers remains a key challenge.

Keywords

Main Subjects