Implementing Box–Cox Quantile Regression
针对Powell提出的Box-Cox分位数回归模型，Chamberlain和Buchinsky的两阶段估计量在第二阶段可能无定义，本文提出一个易于实现的修正估计量，模拟显示修正估计量在原始估计量无定义时表现良好。
The Box-Cox quantile regression model introduced by Powell (1991) is a flexible and numerically attractive extension of linear quantile regression techniques. Chamberlain (1994) and Buchinsky (1995) suggest a two stage estimator for this model but the objective function in stage two of their method may not be defined in an application. We suggest a modification of the estimator which is easy to implement. A simulation study demonstrates that the modified estimator works well in situations, where the original estimator is not well defined.