Non-Linear Effects of the Road Infrastructure on Rural Poverty Incidence in China

Enhancing road infrastructure is a vital component of poverty reduction policies. Using panel data of 31 provincial administrative regions in China from 2013 to 2018, this study aims at applying a Gradient Boosted Decision Tree (GBDT) model to explore the non-linear relationship between road infrastructure variables and rural poverty incidence in two different time periods. Here, the rural poverty incidence was taken as a response variable, and length, density, investment and hardening of road infrastructure were selected as explanatory variables. Results show that the length of highway and village roads present threshold effects on rural poverty incidence, which means poverty alleviation occurs only when they reach a certain scale. The poverty alleviation effects will keep stable after the above indicators exceed their thresholds. These findings could provide helpful references for the planning and construction of rural roads during the transition period between comprehensive poverty alleviation and rural revitalization.