基于正交投影的部分线性空间自回归模型稳健估计

Orthogonal Projection Based Robust Estimation of Partial Linear Spatial Autoregressive Model

本文考虑部分线性空间自回归模型的稳健估计问题。结合矩阵的正交投影技术和分位数回归方法,对模型的参数提出一种新的基于正交投影的稳健估计方法,并在一些正则条件下研究了估计量的渐进性质。最后通过一些数值模拟研究了所提方法的有限样本性质,模拟结果表明所提出的方法具有较好的稳健性。

In this paper, we consider the robust estimation of partial linear spatial autoregressive models. Combining the orthogonal projection technique of matrix and quantile regression method, a new robust estimation method based on orthogonal projection is proposed for the parameters of the model, and the asymptotic properties of the estimator are studied under some regular conditions. Finally, the finite sample properties of the proposed method are studied through some numerical simulations. The simulation results show that the proposed method has good robustness.