LI Shengbiao.Double smoothing estimation for partial linear model with longitudinal data[J].Journal of Yanbian University,2019,45(03):201-207.
纵向数据下部分线性模型的二次光滑估计
- Title:
- Double smoothing estimation for partial linear model with longitudinal data
- 文章编号:
- 1004-4353(2019)03-0201-07
- 分类号:
- O212.1
- 文献标志码:
- A
- 摘要:
- 利用二次光滑估计方法研究纵向数据下部分线性模型的估计问题,给出了二次光滑估计的渐近性质.进一步计算表明,在渐近方差不变的前提下,二次光滑估计的渐近偏差的阶op(h4)低于局部线性估计的渐近偏差的阶op(h2),即二次光滑估计的效果优于局部线性估计的效果.利用CD4细胞数数据对二次光滑估计方法进行验证表明,本文所得结果正确.
- Abstract:
- We used the double smoothing estimation method to discuss the estimation problem of partial linear model, the asymptotic properties of the double smoothing local linear estimators are given. Further calculation show that the order op(h4)of the asymptotic bias of the double smoothing estimation is lower than the order op(h2)of the asymptotic bias of the local linear estimation with the same asymptotic variance, that is to say, the double smoothing estimation is better than the local linear estimation. Using CD4 cell number data to verify the double smoothing local linear estimation method, the results obtained in this paper are correct.
参考文献/References:
[1] ZEGER S L, DIGGLE P J. Semiparametric models for longitudinal data with application to CD4 cell numbers in HIV seroconverters[J]. Biometrics, 1994,50:689-699.
[2] FAN J. Local linear regression smoothers and their minimax efficiency[J]. The Annals of Statistics, 1993,21:196-216.
[3] LIN X H, CARROL R J. Semiparametric regression for clustered data using generalized estimating equations[J]. Journal of the American Statistical Association, 2001,96:1045-1056.
[4] HE H, HUANG L S. Double-smoothing for bias reduction in local linear regression[J]. Journal of Statistical Planning and Inference, 2009,139(3):1056-1072.
[5] HE H, TANG W. Statistical inference in the partial linear models with the double smoothing local linear regression method[J]. Journal of Statistical Planning and Inference, 2014,146:102-112.
[6] HWANG R C, KEN M L. Double smoothing estimation of the multivariate regression function in nonparametric regression[J]. Comm Statist Theory Methods, 2002,31(3):419-434.
[7] HE X M, ZHU Z Y. Estimation in a semiparametric model for longitudinal data with unspecifed dependence structure[J]. Biometrika, 2002,89:579-590.
[8] 樊明智.纵向数据下部分线性模型的渐近性质[J].数理统计与管理,2012,31(3):447-454.
[9] HE H, TANG W, ZUO G X. Statistical inference in the partial linear models with the double smoothing local linear regression method[J]. Journal of Statistical Planning and Inference, 2014,146:102-112.
[10] FAN J Q, LI R Z. New estimation and model selection procedures for semiparametric modeling in longitudinal data analysis[J]. Journal of the American Statistical Association, 2004,99(467):710-723.
[11] 薛留根.现代统计模型[M].北京:科学出版社,2012:24-32.
[12] 罗羡华,李元,周勇,等.基于纵向数据的半参数变系数部分线性回归模型[J].应用数学学报,2007,30(3):540-554.
[13] HALL P, MARRON J S. Smoothed cross validation Probab[J]. Theory Related Field, 1992,90:149-173.
备注/Memo
收稿日期: 2019-06-15
基金项目: 甘肃省教育科学“十三五”规划项目(GHB0372)
作者简介: 李生彪(1981—),男,副教授,研究方向为数理统计及数学建模.