Using Model Selection Criteria to Choose the Number of Principal Components

被引：4
作者：
Sclove, Stanley L. [1 ]
机构：
[1] Univ Illinois, Chicago, IL 60607 USA
来源：
JOURNAL OF STATISTICAL THEORY AND APPLICATIONS | 2021年 / 20卷 / 03期
关键词：
Information criteria; AIC; BIC; Principal components; REGRESSION;
D O I：
10.1007/s44199-021-00002-4
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：
The use of information criteria, especially AIC (Akaike's information criterion) and BIC (Bayesian information criterion), for choosing an adequate number of principal components is illustrated.
引用
收藏
页码：450 / 461
页数：12
相关论文
共 14 条
  • [11] Feature Selection for Classification using Principal Component Analysis and Information Gain
    Omuya, Erick Odhiambo
    Okeyo, George Onyango
    Kimwele, Michael Waema
    [J]. EXPERT SYSTEMS WITH APPLICATIONS, 2021, 174
  • [12] ESTIMATING DIMENSION OF A MODEL
    SCHWARZ, G
    [J]. ANNALS OF STATISTICS, 1978, 6 (02) : 461 - 464
  • [13] APPLICATION OF MODEL-SELECTION CRITERIA TO SOME PROBLEMS IN MULTIVARIATE-ANALYSIS
    SCLOVE, SL
    [J]. PSYCHOMETRIKA, 1987, 52 (03) : 333 - 343
  • [14] The fuzzy comprehensive evaluation (FCE) and the principal component analysis (PCA) model simulation and its applications in water quality assessment of Nansi Lake Basin, China
    Xu, Shiguo
    Cui, Yixiao
    Yang, Chuanxi
    Wei, Shujing
    Dong, Wenping
    Huang, Lihui
    Liu, Changqing
    Ren, Zongming
    Wang, Weiliang
    [J]. ENVIRONMENTAL ENGINEERING RESEARCH, 2021, 26 (02)
12