Bayesian Factor Analysis as a Variable-Selection Problem: Alternative Priors and Consequences.

Bayesian Factor Analysis as a Variable-Selection Problem: Alternative Priors and Consequences.
复制标题

DOI:
10.1080/00273171.2016.1168279
复制
发表时间:
2016-07
影响因子:
3.8
通讯作者:
Loken E
Loken E
中科院分区:
心理学3区
文献类型:
--
作者:
Lu ZH;Chow SM;Loken E

文献摘要

参考文献

被引文献

相似文献

因子分析是一种流行的多元数据分析方法。结构方程模型框架的发展使混合验证性/探索性方法的使用成为可能,在这种方法中,可以在验证性因素分析(CFA)框架内相对灵活地探索因素加载结构。最近,贝叶斯结构方程模型(BSEM)方法已被提出作为一种方法来探索CFA模型中存在的交叉负荷。我们发现,决定因素的加载模式的问题可以制定为贝叶斯变量选择问题,其中Muthén和Asparouhov的方法可以被视为一个BSEM方法与岭回归先验(BSEM-RP)。我们提出了另一种贝叶斯方法,在这里表示为贝叶斯结构方程模型与尖峰和板前(BSEM-SSP),它作为一个阶段的替代BSEM-RP。我们回顾了这两种方法的理论优势和不足,并比较了它们相对于两种基于修正指数的方法和具有目标旋转的探索性因子分析的实证表现。教师压力量表的数据集被用来证明我们的方法。
Factor analysis is a popular statistical technique for multivariate data analysis. Developments in the structural equation modeling framework have enabled the use of hybrid confirmatory/exploratory approaches in which factor loading structures can be explored relatively flexibly within a confirmatory factor analysis (CFA) framework. Recently, a Bayesian structural equation modeling (BSEM) approach has been proposed as a way to explore the presence of cross-loadings in CFA models. We show that the issue of determining factor loading patterns may be formulated as a Bayesian variable selection problem in which Muthén and Asparouhov’s approach can be regarded as a BSEM approach with ridge regression prior (BSEM-RP). We propose another Bayesian approach, denoted herein as the Bayesian structural equation modeling with spike and slab prior (BSEM-SSP), which serves as a one-stage alternative to the BSEM-RP. We review the theoretical advantages and disadvantages of both approaches and compare their empirical performance relative to two modification indices-based approaches and exploratory factor analysis with target rotation. A teacher stress scale data set is used to demonstrate our approach.
DOI: 10.2307/2983440
发表时间: 1995-01-01
影响因子: 2
作者:
CHATFIELD, C
通讯作者: CHATFIELD, C
DOI: 10.3102/00028312031003645
发表时间: 1994-09-01
影响因子: 3.6
作者:
BYRNE, BM
通讯作者: BYRNE, BM
DOI: 10.1080/00401706.1970.10488634
发表时间: 1970-01-01
期刊: TECHNOMETRICS
影响因子: 2.5
作者:
HOERL, AE;KENNARD, RW
通讯作者: KENNARD, RW
DOI: 10.1080/10705510903008204
发表时间: 2009-01-01
影响因子: 6
作者:
Asparouhov, Tihomir;Muthen, Bengt
通讯作者: Muthen, Bengt
DOI: 10.1080/00273171.2012.732901
发表时间: 2012-11
影响因子: 3.8
作者:
Cham H;West SG;Ma Y;Aiken LS
通讯作者: Aiken LS