...
首页> 外文期刊>Journal of statistical computation and simulation >Statistical inference for varying-coefficient models with error-prone covariates
【24h】

Statistical inference for varying-coefficient models with error-prone covariates

机译:具有易错协变量的变系数模型的统计推断

获取原文
获取原文并翻译 | 示例
           

摘要

Motivated by an application, we consider the statistical inference of varying-coefficient regression models in which some covariates are not observed, but ancillary variables are available to remit them. Due to the attenuation, the usual local polynomial estimation of the coefficient functions is not consistent. We propose a corrected local polynomial estimation for the unknown coefficient functions by calibrating the error-prone covariates. It is shown that the resulting estimators are consistent and asymptotically normal. In addition, we develop a wild bootstrap test for the goodness of fit of models. Some simulations are conducted to demonstrate the finite sample performances of the proposed estimation and test procedures. An example of application on a real data from Duchenne muscular dystrophy study is also illustrated.
机译:出于应用程序的考虑,我们考虑了变化系数回归模型的统计推断,在该模型中未观察到某些协变量,但是可以使用辅助变量来缓解这些协变量。由于衰减,系数函数的常规局部多项式估计不一致。我们通过校准容易出错的协变量,为未知系数函数提出了校正后的局部多项式估计。结果表明,所得的估计量是一致的,并且是渐近正态的。此外,我们针对模型的拟合优度开发了野生引导测试。进行了一些模拟,以证明所提出的估计和测试程序的有限样本性能。还举例说明了从杜氏肌营养不良症研究获得的真实数据的应用示例。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号