arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1603.04093stat.ME
收藏

调整后的Jackknife经验似然法

Adjusted Jackknife Empirical Likelihood

Ying-Ju Chen, Wei Ning

摘要:

刀切经验似然法(Jackknife Empirical Likelihood,JEL)是经验似然法(Empirical Likelihood,EL)的一种有效的改进形式.通过构造刀切伪值,JEL方法克服了EL方法在非线性约束条件下的计算困难,同时保持了单样本和双样本U统计量相同的渐近结果.在本文中,我们提出了一个调整版本的JEL,以保证调整后的刀切经验似然(AJEL)统计量是定义良好的所有值的参数,而不是限制在凸包的估计方程。为AJEL保留了JEL的属性。

英文摘要:

Jackknife empirical likelihood (JEL) is an effective modified version of empirical likelihood method (EL). Through the construction of the jackknife pseudo-values, JEL overcomes the computational difficulty of EL method when its constraints are nonlinear while maintaining the same asymptotic results for one sample and two-sample U statistics. In this paper, we propose an adjusted version of JEL to guarantee that the adjusted jackknife empirical likelihood (AJEL) statistic is well-defined for all the values of the parameter, instead of restricting on the convex hull of the estimation equation. The properties of JEL have been preserved for AJEL.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑