关键词: 分位数回归, 部分线性单指数面板模型, 样条函数

Abstract: Quantile regression is a useful supplement to mean regression. The method needn’t assume specification of distribution and is robust to outlie or heavy tail distribution of data. Most previous studies on partially linear single index models concentrated on mean regression. Based on this, this paper investigated quantile regression of partially linear single index panel models with fixed effect. We estimated the model based on the combination of B spline function, SCAD penalized function and reweighted least squares algorithm, and proved the consistence and asymptotic normality of estimators. Also, we evaluated the finite sample performance of the proposed method via Monte Carlo simulation. Furthermore, the proposed method is illustrated in factor analysis of carbon emissions.

Key words: Quantile Regression, Partially Linear Single Index Panel Models, Spline Function