Robust small area estimation under semi-parametric mixed models

被引：15

作者：

Rao, Jon N. K. ^{[1
]}

Sinha, Sanjoy K. ^{[1
]}

Dumitrescu, Laura ^{[1
]}

机构：

[1] Carleton Univ, Sch Math & Stat, Ottawa, ON K1S 5B6, Canada

来源：

CANADIAN JOURNAL OF STATISTICS-REVUE CANADIENNE DE STATISTIQUE | 2014年 / 42卷 / 01期

基金：

加拿大自然科学与工程研究理事会;

关键词：

Mean squared prediction error; outliers; unit level model; secondary; 62F35; Primary; 62F10; MSC 2010:; Bootstrap; random effects; small area mean; PREDICTION; ERROR;

D O I：

10.1002/cjs.11199

中图分类号：

O21 [概率论与数理统计]; C8 [统计学];

学科分类号：

020208 ; 070103 ; 0714 ;

摘要：

Abstract Small area estimation has been extensively studied under unit level linear mixed models. In particular, empirical best linear unbiased predictors (EBLUPs) of small area means and associated estimators of mean squared prediction error (MSPE) that are unbiased to second order have been developed. However, EBLUP can be sensitive to outliers. Sinha & Rao (2009) developed a robust EBLUP method and demonstrated its advantages over the EBLUP in the presence of outliers in the random small area effects and/or unit level errors in the model. A bootstrap method for estimating MSPE of the robust EBLUP was also proposed. In this paper, we relax the assumption of linear regression for the fixed part of the model and we replace it by a weaker assumption of a semi-parametric regression. By approximating the semi-parametric mixed model by a penalized spline mixed model, we develop robust EBLUPs of small area means and bootstrap estimators of MSPE. Results of a simulation study are also presented. The Canadian Journal of Statistics 42: 126-141; 2014 (c) 2013 Statistical Society of Canada

引用

页码：126 / 141

页数：16

共 21 条

[11]

Jiang J., 2010, SPRINGER TEXTS STAT, DOI DOI 10.1007/978-1-4419-6827-2

[12] Mixed model prediction and small area estimation [J].

Jiang, Jiming ;

Lahiri, P. .

TEST, 2006, 15 (01) :1-59

[13]

Jiang JM, 1996, ANN STAT, V24, P255

[14] The role of pseudo data for robust smoothing with application to wavelet regression [J].

Oh, Hee-Seok ;

Nychka, Douglas W. ;

Lee, Thomas C. M. .

BIOMETRIKA, 2007, 94 (04) :893-904

[15] Non-parametric small area estimation using penalized spline regression [J].

Opsomer, J. D. ;

Claeskens, G. ;

Ranalli, M. G. ;

Kauermann, G. ;

Breidt, F. J. .

JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES B-STATISTICAL METHODOLOGY, 2008, 70 :265-286

[16] Small-area estimation under informative probability sampling of areas and within the selected areas [J].

Pfeffermann, Danny ;

Sverchkov, Michail .

JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 2007, 102 (480) :1427-1439

[17]

Rao J. N. K., 2003, SMALL AREA ESTIMATIO, DOI DOI 10.1002/0471722189

[18] Robust model selection using fast and robust bootstrap [J].

Salibian-Barrera, Matlas ;

Van Aelst, Stefan .

COMPUTATIONAL STATISTICS & DATA ANALYSIS, 2008, 52 (12) :5121-5135

[19] Robust small area estimation [J].

Sinha, Sanjoy K. ;

Rao, J. N. K. .

CANADIAN JOURNAL OF STATISTICS-REVUE CANADIENNE DE STATISTIQUE, 2009, 37 (03) :381-399

[20] Approaches to robust estimation in the simplest variance components model [J].

Stahel, WA ;

Welsh, A .

JOURNAL OF STATISTICAL PLANNING AND INFERENCE, 1997, 57 (02) :295-319

← 1 2 3 →