Yingnan ZHANG, School of Public Affairs, Zhejiang University, China
Shuocun CHEN, School of Public Affairs, Zhejiang University, China
Li MA, School of Public Affairs?Chongqing University, China
Recent years have witnessed a dramatic decrease in the cultivation of non-grain products in rural China, which arises a global concern. Although a significant amount of research has been done studying the driving forces of non-grain preference at household level, village-level factors are ignored. In general, what contributes to the substitution of grains in production has not been well elucidated. There is a growing need to understand the reasons for the non-grain production preference to aid further agricultural development and ensure grain security. This paper attempts to investigate the factors that increases the non-grain crops through quantitative analysis of 306 villages in China. In addition to OLS estimation, we apply Boosted Regression Trees (BRT), a machine learning algorithm that combines the strengths of decision trees and boosting, to identify the determinants of non-grain production, which is an effective technique that can economically handle factors with many levels and possible nonlinear interactions between explanatory variables.
Mots clés : Food security|non-grain preference|farmland management
A104085YZ