A Paradoxical Result in Estimating Regression Coefficients

被引：10

作者：

Tarpey, Thaddeus ^{[1
]}

Ogden, R. Todd ^{[2
]}

Petkova, Eva ^{[3
,4
]}

Christensen, Ronald ^{[5
]}

机构：

[1] Wright State Univ, Dept Math & Stat, Dayton, OH 45435 USA

[2] Columbia Univ, Dept Biostat, Mailman Sch Publ Hlth, New York, NY 10032 USA

[3] NYU, Dept Child & Adolescent Psychiat, New York, NY 10016 USA

[4] Nathan S Kline Inst Psychiat Res, Orangeburg, NY 10962 USA

[5] Univ New Mexico, Dept Math & Stat, Albuquerque, NM USA

来源：

AMERICAN STATISTICIAN | 2014年 / 68卷 / 04期

关键词：

Jensen's inequality; Ratio estimator; Pooled variance estimator; Moderator analysis;

D O I：

10.1080/00031305.2014.940467

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：

This article presents a counterintuitive result regarding the estimation of a regression slope coefficient. Paradoxically, the precision of the slope estimator can deteriorate when additional information is used to estimate its value. In a randomized experiment, the distribution of baseline variables should be identical across treatments due to randomization. The motivation for this article came from noting that the precision of slope estimators deteriorated when pooling baseline predictors across treatment groups.

引用

页码：271 / 276

页数：6

共 50 条

[21] Optimal designs for estimating individual coefficients in polynomial regression - a functional approach
Dette, H
Melas, VB
Pepelyshev, A
JOURNAL OF STATISTICAL PLANNING AND INFERENCE, 2004, 118 (1-2) : 201 - 219
[22] Estimating atmospheric pressure loading regression coefficients from GPS observations
Klaus Kaniuth
Sandra Vetter
GPS Solutions, 2006, 10 : 126 - 134
[23] Estimating spatial quantile regression with functional coefficients: A robust semiparametric framework
Lu, Zudi
Tang, Qingguo
Cheng, Longsheng
BERNOULLI, 2014, 20 (01) : 164 - 189
[24] Estimating coefficients of single-index regression models by minimizing variation
Lou, Dongfang
Ma, Zhiyuan
JOURNAL OF STATISTICAL COMPUTATION AND SIMULATION, 2018, 88 (02) : 343 - 358
[25] Estimating atmospheric pressure loading regression coefficients from GPS observations
Klaus Kaniuth
Sandra Vetter
GPS Solutions, 2006, 10 (2) : 135 - 135
[26] Optimal designs for estimating the coefficients of the lower frequencies in trigonometric regression models
Dette, Holger
Melas, Viatcheslav B.
Shpilev, Piter
ANNALS OF THE INSTITUTE OF STATISTICAL MATHEMATICS, 2007, 59 (04) : 655 - 673
[27] ESTIMATING THE ERROR VARIANCE IN REGRESSION AFTER A PRELIMINARY TEST OF RESTRICTIONS ON THE COEFFICIENTS
CLARKE, JA
GILES, DEA
WALLACE, TD
JOURNAL OF ECONOMETRICS, 1987, 34 (03) : 293 - 304
[28] Rates of convergence for estimating regression coefficients in heteroskedastic discrete response models
Chen, SN
Khan, S
JOURNAL OF ECONOMETRICS, 2003, 117 (02) : 245 - 278
[29] Optimal designs for estimating the coefficients of the lower frequencies in trigonometric regression models
Holger Dette
Viatcheslav B. Melas
Piter Shpilev
Annals of the Institute of Statistical Mathematics, 2007, 59 : 655 - 673
[30] AN EXPERIMENTAL INVESTIGATION OF THE ROBUSTNESS OF CERTAIN PROCEDURES FOR ESTIMATING MEANS AND REGRESSION-COEFFICIENTS
CHAMPERNOWNE, DG
JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES A-GENERAL, 1960, 123 (04): : 398 - 412

← 1 2 3 4 5 →