Choosing principal components: A new graphical method based on bayesian model selection

被引：17

作者：

Auer, Philipp ^{[2
]}

Gervini, Daniel ^{[1
]}

机构：

[1] Univ Wisconsin, Dept Math Sci, Milwaukee, WI 53201 USA

[2] Munchener Ruckversicherungs Gesell, Munich, Germany

来源：

COMMUNICATIONS IN STATISTICS-SIMULATION AND COMPUTATION | 2008年 / 37卷 / 05期

关键词：

dimension reduction; factor analysis; scree plot; singular value decomposition;

D O I：

10.1080/03610910701855005

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 approaches the problem of selecting significant principal components from a Bayesian model selection perspective. The resulting Bayes rule provides a simple graphical technique that can be used instead of (or together with) the popular scree plot to determine the number of significant components to retain. We study the theoretical properties of the new method and show, by examples and simulation, that it provides more clear-cut answers than the scree plot in many interesting situations.

引用

页码：962 / 977

页数：16

共 50 条

[1] A Method for Principal Components Selection Based on Stochastic Matrix
Zhang, Yangwu
Li, Guohe
Wang, Limei
Zong, Heng
Zhao, Jingming
[J]. 2017 13TH INTERNATIONAL CONFERENCE ON NATURAL COMPUTATION, FUZZY SYSTEMS AND KNOWLEDGE DISCOVERY (ICNC-FSKD), 2017,
[2] Bayesian Ising Graphical Model for Variable Selection
Fang, Zaili
Kim, Inyoung
[J]. JOURNAL OF COMPUTATIONAL AND GRAPHICAL STATISTICS, 2016, 25 (02) : 589 - 605
[3] Efficient Bayesian Regularization for Graphical Model Selection
Kundu, Suprateek
Mallick, Bani K.
Baladandayuthapani, Veera
[J]. BAYESIAN ANALYSIS, 2019, 14 (02): : 449 - 476
[4] A Graphical Method for Model Selection
Boiroju, Naveen Kumar
Reddy, M. Krishna
[J]. PAKISTAN JOURNAL OF STATISTICS AND OPERATION RESEARCH, 2012, 8 (04) : 767 - 776
[5] A New Indoor Localization System Based on Bayesian Graphical Model
Alhammadi, Abdulraqeb
Hashim, Fazirulhiysam
Rasid, Mohd Fadlee A.
Alraih, Saddam
[J]. 2017 2ND IEEE INTERNATIONAL CONFERENCE ON WIRELESS COMMUNICATIONS, SIGNAL PROCESSING AND NETWORKING (WISPNET), 2017, : 1960 - 1964
[6] A selection index based on principal components
Cerón-Rojas, JJ
Sahagún-Castellanos, J
[J]. AGROCIENCIA, 2005, 39 (06) : 667 - 677
[7] Objective Bayesian model selection in Gaussian graphical models
Carvalho, C. M.
Scott, J. G.
[J]. BIOMETRIKA, 2009, 96 (03) : 497 - 512
[8] VARIABLE SELECTION CRITERIA-BASED ON SPECIFIC GAUSSIAN GRAPHICAL MODELS IN PRINCIPAL-COMPONENTS ANALYSIS
DEFALGUEROLLES, A
JMEL, S
[J]. CANADIAN JOURNAL OF STATISTICS-REVUE CANADIENNE DE STATISTIQUE, 1993, 21 (03): : 239 - 256
[9] The Method of Trajectory Selection Based on Bayesian Game Model
Tian, Wen
Fang, Qin
Zhou, Xuefang
Yang, Fan
[J]. SUSTAINABILITY, 2022, 14 (18)
[10] Robust Bayesian model selection for variable clustering with the Gaussian graphical model
Daniel Andrade
Akiko Takeda
Kenji Fukumizu
[J]. Statistics and Computing, 2020, 30 : 351 - 376

← 1 2 3 4 5 →