Inference based on many conditional moment inequalities
Inference based on many conditional moment inequalities
复制标题
基于许多条件矩不等式的推理
DOI：
10.1016/j.jeconom.2016.09.010
复制
发表时间：
2017
影响因子：
6.3
通讯作者：
Shi, Xiaoxia
中科院分区：
文献类型：
--
作者：
Andrews, Donald W.K.;Shi, Xiaoxia
我们为由许多条件矩不等式/等式定义的模型构造置信集。条件矩限制的数量可以达到无限多。为了处理大量的矩限制，我们利用了矩函数类的可管理性（Pollard(1990)）。我们从最近的部分鉴定文献中的五个例子验证了这一条件。结果表明，置信集具有正确的均匀渐近大小，并以接近1的概率排除识别集之外的参数值。蒙特卡罗实验对一个条件随机优势的例子和一个随机系数二元结果的例子支持了理论结果。
We construct confidence sets for models defined by many conditional moment inequalities/equalities. The number of conditional moment restrictions can be up to infinitely many. To deal with the vast number of moment restrictions, we exploit the manageability (Pollard (1990)) of the class of moment functions. We verify this condition in five examples from the recent partial identification literature.The confidence sets are shown to have correct uniform asymptotic size and to exclude parameter values outside the identified set with probability approaching one. Monte Carlo experiments for a conditional stochastic dominance example and a random-coefficient binary-outcome example support the theoretical results.