Interpretation of partial least-squares regression models with VARIMAX rotation

Huiwen Wang; Qiang Liu; Yongping Tu

doi:10.1016/j.csda.2003.12.005

Interpretation of partial least-squares regression models with VARIMAX rotation

Huiwen Wang^*
, Qiang Liu
, Yongping Tu

^*Corresponding author for this work

Beihang University

Research output: Contribution to journal › Article › peer-review

22 Scopus citations

Abstract

The VARIMAX rotation for factor analysis is used to orthogonally transform the factor subspace, resulting from partial least-square regression (PLSR). If the factors are nearly orthogonal, the transformation may help to interpret the physical meaning of each factor without altering the results of a PLSR model. A case study shows that after the VARIMAX rotation, the loading matrix satisfies "the simple structure criterion" and improves its explanatory ability.

Original language	English
Pages (from-to)	207-219
Number of pages	13
Journal	Computational Statistics and Data Analysis
Volume	48
Issue number	1
DOIs	https://doi.org/10.1016/j.csda.2003.12.005
State	Published - 1 Jan 2005

Keywords

Factor analysis
Factor subspace
Partial least-squares regression
VARIMAX rotation

Access to Document

10.1016/j.csda.2003.12.005

Cite this

@article{a69d643c3a994f888bdb493c8272f574,

title = "Interpretation of partial least-squares regression models with VARIMAX rotation",

abstract = "The VARIMAX rotation for factor analysis is used to orthogonally transform the factor subspace, resulting from partial least-square regression (PLSR). If the factors are nearly orthogonal, the transformation may help to interpret the physical meaning of each factor without altering the results of a PLSR model. A case study shows that after the VARIMAX rotation, the loading matrix satisfies {"}the simple structure criterion{"} and improves its explanatory ability.",

keywords = "Factor analysis, Factor subspace, Partial least-squares regression, VARIMAX rotation",

author = "Huiwen Wang and Qiang Liu and Yongping Tu",

year = "2005",

month = jan,

day = "1",

doi = "10.1016/j.csda.2003.12.005",

language = "英语",

volume = "48",

pages = "207--219",

journal = "Computational Statistics and Data Analysis",

issn = "0167-9473",

publisher = "Elsevier B.V.",

number = "1",

}

TY - JOUR

T1 - Interpretation of partial least-squares regression models with VARIMAX rotation

AU - Wang, Huiwen

AU - Liu, Qiang

AU - Tu, Yongping

PY - 2005/1/1

Y1 - 2005/1/1

N2 - The VARIMAX rotation for factor analysis is used to orthogonally transform the factor subspace, resulting from partial least-square regression (PLSR). If the factors are nearly orthogonal, the transformation may help to interpret the physical meaning of each factor without altering the results of a PLSR model. A case study shows that after the VARIMAX rotation, the loading matrix satisfies "the simple structure criterion" and improves its explanatory ability.

AB - The VARIMAX rotation for factor analysis is used to orthogonally transform the factor subspace, resulting from partial least-square regression (PLSR). If the factors are nearly orthogonal, the transformation may help to interpret the physical meaning of each factor without altering the results of a PLSR model. A case study shows that after the VARIMAX rotation, the loading matrix satisfies "the simple structure criterion" and improves its explanatory ability.

KW - Factor analysis

KW - Factor subspace

KW - Partial least-squares regression

KW - VARIMAX rotation

UR - https://www.scopus.com/pages/publications/10144230052

U2 - 10.1016/j.csda.2003.12.005

DO - 10.1016/j.csda.2003.12.005

M3 - 文章

AN - SCOPUS:10144230052

SN - 0167-9473

VL - 48

SP - 207

EP - 219

JO - Computational Statistics and Data Analysis

JF - Computational Statistics and Data Analysis

IS - 1

ER -

Interpretation of partial least-squares regression models with VARIMAX rotation

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this