摘要
In this paper we propose a method to approximate a class of statistics which admit Edgeworth expansions. The accuracy of the approximation is proved to be at the same optimal rate as the well known bootstrap and random weighting. In practice conditional distributions of uni-dimensional statistics constructed by our method can exactly be derived. Meanwhile, our method has a nice model robustness.
In this paper we propose a method to approximate a class of statistics which admit Edgeworth expansions. The accuracy of the approximation is proved to be at the same optimal rate as the well known bootstrap and random weighting. In practice conditional distributions of uni-dimensional statistics constructed by our method can exactly be derived. Meanwhile, our method has a nice model robustness.
