Non-crossing convex quantile regression
针对形状约束非参数分位数回归中的分位数交叉问题，提出一种惩罚凸分位数回归方法，在避免交叉的同时保持分位数性质，蒙特卡洛模拟显示其优越性。
Quantile crossing is a common phenomenon in shape constrained nonparametric quantile regression. A direct approach to address this problem is to impose non-crossing constraints to convex quantile regression. However, the non-crossing constraints may violate an intrinsic quantile property. This paper proposes a penalized convex quantile regression approach that can circumvent quantile crossing while maintaining the quantile property. A Monte Carlo study demonstrates the superiority of the proposed penalized approach in addressing the quantile crossing problem.