The Open UniversitySkip to content

Exploratory factor analysis of data matrices with more variables than observations

Trendafilov, Nickolay T. and Unkel, Steffen (2011). Exploratory factor analysis of data matrices with more variables than observations. Journal of Computational and Graphical Statistics, 20(4) pp. 874–891.

DOI (Digital Object Identifier) Link:
Google Scholar: Look up in Google Scholar


A new approach for exploratory factor analysis (EFA) of data matrices with more variables p than observations n is presented. First, the classic EFA model (n > p) is considered as a specific data matrix decomposition with fixed unknown matrix parameters. Then, it is generalized to a new model, called for short GEFA, which covers both cases of data, with either n > p or pn. An alternating least squares algorithm GEFALS is proposed for simultaneous estimation of all GEFA model parameters. As principal component analysis (PCA), GEFALS is based on singular value decomposition, which makes GEFA an attractive alternative to PCA for descriptive data analysis and dimensionality reduction. The existence and uniqueness of the GEFA parameters estimations is studied and the convergence properties of GEFALS are established. Finally, the new approach is illustrated with Thurstone's 26-variable box data and real high-dimensional data, while the performance of GEFALS - with simulation experiment.

Item Type: Journal Article
Copyright Holders: 2011 American Statistical Association, Institute of Mathematical Statistics, and Interface Foundation of North America
ISSN: 1537-2715
Keywords: factor analysis; p > n; Procrustes problem; singular value decomposition
Academic Unit/Department: Mathematics, Computing and Technology > Mathematics and Statistics
Mathematics, Computing and Technology
Related URLs:
Item ID: 29120
Depositing User: Sara Griffin
Date Deposited: 18 Jul 2011 09:08
Last Modified: 18 Jan 2016 10:39
Share this page:


Scopus Citations

▼ Automated document suggestions from open access sources

Actions (login may be required)

Policies | Disclaimer

© The Open University   + 44 (0)870 333 4340