A RESAMPLING METHOD BASED ON PIVOTAL ESTIMATING FUNCTIONS
A RESAMPLING METHOD BASED ON PIVOTAL ESTIMATING FUNCTIONS
复制标题
DOI：
10.2307/2336964
复制
发表时间：
1994-06-01
期刊：
影响因子：
2.7
通讯作者：
YING, Z
中科院分区：
文献类型：
--
作者：
PARZEN, MI;WEI, LJ;YING, Z
假设在半参数模型设置下，人们有兴趣根据估计函数对有限维参数向量 beta 进行推断。一般来说，通过找到相应估计方程的根，可以轻松获得 beta0 的一致点估计器 beta（beta 的真实值）。然而，估计 beta 的方差可能涉及复杂且主观的非参数函数估计。本文提出了一种基于关键估计函数的用于推断 beta0 的通用且简单的重采样方法。新程序通过分位数和排名回归模型进行说明。对于这两种情况，我们的建议都可以使用现有的统计软件轻松有效地实施。
Suppose that, under a semiparametric model setting, one is interested in drawing inferences about a finite-dimensional parameter vector beta based on an estimating function. Generally a consistent point estimator beta for beta0, the true value for beta, can be easily obtained by finding a root of the corresponding estimating equation. To estimate the variance of beta, however, may involve complicated and subjective nonparametric functional estimates. In this paper, a general and simple resampling method for inferences about beta0 based on pivotal estimating functions's proposed. The new procedure is illustrated with the quantile and rank regression models. For both cases, our proposal can be easily and efficiently implemented with existing statistical software.