NONPARAMETRIC COINTEGRATING REGRESSION WITH NNH ERRORS
研究带有非线性非平稳异方差误差过程的非线性协整回归模型，证明了常规核估计的一致收敛性，并提出了两阶段方法估计异质性生成函数。
This paper studies a nonlinear cointegrating regression model with nonlinear nonstationary heteroskedastic error processes. We establish uniform consistency for the conventional kernel estimate of the unknown regression function and develop atwo-stage approach for the estimation of the heterogeneity generating function.