Solving the sign indeterminacy for multiway models

Bilinear and multilinear models such as principal component analysis and PARAFAC have intrinsic sign indeterminacies. For example, any loading vector can be multiplied by −1 if another vector of that particular component is also multiplied by −1 without affecting the loss function values. This sometimes causes problems, for example, with respect to interpretation. In this paper, a method is developed to fix the sign indeterminacy for the PARAFAC, Tucker3 and PARAFAC2 models. Copyright © 2013 John Wiley & Sons, Ltd.

[1]  J. Leeuw,et al.  Principal component analysis of three-mode data by means of alternating least squares algorithms , 1980 .

[2]  Pieter M. Kroonenberg,et al.  Three-mode principal component analysis : theory and applications , 1983 .

[3]  Riccardo Leardi,et al.  Three‐mode principal component analysis of monitoring data from Venice lagoon , 2000 .

[4]  R. Bro.  PARAFAC. Tutorial and applications , 1997 .

[5]  Karl Pearson F.R.S..  LIII. On lines and planes of closest fit to systems of points in space , 1901 .

[6]  R. Bro,et al.  Resolving the sign ambiguity in the singular value decomposition , 2008 .

[7]  M. Klapa,et al.  Standardizing GC-MS metabolomics. , 2008, Journal of chromatography. B, Analytical technologies in the biomedical and life sciences.

[8]  B. Everitt,et al.  Three-Mode Principal Component Analysis. , 1986 .

[9]  Rasmus Bro,et al.  Classification of GC‐MS measurements of wines by combining data dimension reduction and variable selection techniques , 2008 .

[10]  Rasmus Bro,et al.  MULTI-WAY ANALYSIS IN THE FOOD INDUSTRY Models, Algorithms & Applications , 1998 .

[11]  Pieter M. Kroonenberg,et al.  The TUCKALS line: a suite of programs for three-way data analysis , 1994 .

[12]  H. Kiers.  Towards a standardized notation and terminology in multiway analysis , 2000 .

[13]  H. Hotelling.  Analysis of a complex of statistical variables into principal components. , 1933 .

[14]  J. Edward Jackson,et al.  Principal Components and Factor Analysis: Part I - Principal Components , 1980 .

[15]  Richard A. Harshman,et al.  Foundations of the PARAFAC procedure: Models and conditions for an "explanatory" multi-model factor analysis , 1970 .