Local constant kernel-weighted quantile regression estimation via an MM-algorithm and its applications

A new local constant kernel weighted computational method based on MM-algorithm is proposed in this paper. The proposed method makes that the calculated quantile regression estimation curve is continuous and smooth under some mild conditions. The selection problem of the tuning parameter is also discussed. Finally, simulation studies and a real data analysis illustrate that the quantile regression estimation curve based on our proposed computational method is robust under the model with heavy-tailed error.