Does adding data always improve linear regression estimates?

被引：1
|
作者：
den Boer, A. V. [1 ]
机构：
[1] Eindhoven Univ Technol, NL-5600 MB Eindhoven, Netherlands
来源：
STATISTICS & PROBABILITY LETTERS | 2013年 / 83卷 / 03期
关键词：
Least-squares linear regression; Strong consistency; Inconsistency;
D O I：
10.1016/j.spl.2012.12.001
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：
Intuitively one might expect that the quality of statistical estimates cannot worsen if they are based on more data. We show in a least-squares linear regression setting that this intuition is wrong. Adding data may worsen the quality of parameter estimates, and in fact may even cause a design sequence to lose strong consistency. (C) 2012 Elsevier B.V. All rights reserved.
引用
收藏
页码：829 / 835
页数：7
相关论文
共 50 条
  • [1] ON LINEAR REGRESSION ESTIMATES
    TEMPELMA.AA
    DOKLADY AKADEMII NAUK SSSR, 1970, 191 (04): : 772 - &
  • [2] Does deep learning always outperform simple linear regression in optical imaging?
    Jiao, Shuming
    Gao, Yang
    Feng, Jun
    Lei, Ting
    Yuan, Xiaocong
    OPTICS EXPRESS, 2020, 28 (03): : 3717 - 3731
  • [3] Asymptotic Degradation of Linear Regression Estimates with Strategic Data Sources
    Roussillon, Benjamin
    Gast, Nicolas
    Loiseau, Patrick
    Mertikopoulos, Panayotis
    INTERNATIONAL CONFERENCE ON ALGORITHMIC LEARNING THEORY, VOL 167, 2022, 167
  • [4] Fuzzy estimates of regression parameters in linear regression models for imprecise input and output data
    Wu, HC
    COMPUTATIONAL STATISTICS & DATA ANALYSIS, 2003, 42 (1-2) : 203 - 217
  • [5] Nonparametric regression estimates with censored data: Local linear smoothers and their applications
    Kim, HT
    Truong, YK
    BIOMETRICS, 1998, 54 (04) : 1434 - 1444
  • [6] Nonparametric regression estimates with censored data: Local linear smoothers and their applications
    Department of Biostatistics, Graduate School of Public Health, University Pittsburgh, 130 DeSoto Street, Pittsburgh, PA 15261, United States
    不详
    Biometrics, 4 (1434-1444):
  • [7] Does adding clinical data to administrative data improve agreement among hospital quality measures?
    Hanchate, Amresh D.
    Stolzmann, Kelly L.
    Rosen, Amy K.
    Fink, Aaron S.
    Shwartz, Michael
    Ash, Arlene S.
    Abdulkerim, Hassen
    Pugh, Mary Jo V.
    Shokeen, Priti
    Borzecki, Ann
    HEALTHCARE-THE JOURNAL OF DELIVERY SCIENCE AND INNOVATION, 2017, 5 (03): : 112 - 118
  • [8] Does equating always improve score comparability?
    Xie, XQ
    INTERNATIONAL JOURNAL OF PSYCHOLOGY, 2004, 39 (5-6) : 374 - 374
  • [9] Adding an antidepressant does not improve bipolar depression
    不详
    JOURNAL OF FAMILY PRACTICE, 2007, 56 (08): : 616 - 616
  • [10] Tracking maneuvering targets with multiple sensors: Does more data always mean better estimates?
    Blair, WD
    BarShalom, Y
    IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC SYSTEMS, 1996, 32 (01) : 450 - 456
12345