Abstract
The use and interpretation of scaling factors in generalised Procrustes analysis is discussed. The estimated optimal isotropic scaling factors are shown to include a component for differential weighting of individual configurations as well as a component adjusting for overall size. These separate components are illustrated using a data set from sensory analysis. Separating the components can lead to improved time to convergence as shown in simulation studies.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Arnold, G.M. and Payne, R.W. (1991). Procedure GENPROC. In: ‘Genstat 5 Procedure Library Manual: Release 2[2]’, (ed. R.W. Payne and G.M. Arnold), 111–114. Oxford: Numerical Algorithms Group.
Arnold, G.M. and Williams, A.A. (1986). The use of generalised Procrustes techniques in sensory analysis. In: ’statistical Procedures in Food Research’, (ed. J.R. Piggott), 233–253. London: Elsevier.
Collins, A.J. (1991). The use of generalised Procrustes techniques in sensory analysis. In: ‘Agro-Industrie et Methodes Statistiques’, 2èmes journées européenes, Nantes, 43-54.
Dijksterhuis, G.B. and Gower, J.C. (1991). The interpretation of generalized Procrustes analysis and allied methods. Department of Data Theory, University of Leiden. pp. 56
Gower, J.C. (1975). Generalized Procrustes analysis. Psychometrika, 40, 35–50.
Peay, E.R. (1988). Multidimensional rotation and scaling of configurations to optimal agreement. Psychometrika, 53, 199–208.
Ten Berge, J.M.F. (1977). Orthogonal Procrustes rotation for two or more matrices. Psychometrika, 42, 267–276.
Williams, A.A. and Langron, S.P. (1984). The use of free-choice profiling for the evaluation of commercial ports. J. Sci. Food Agric., 35, 558–568.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1992 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Arnold, G.M. (1992). Scaling Factors in Generalised Procrustes Analysis. In: Dodge, Y., Whittaker, J. (eds) Computational Statistics. Physica, Heidelberg. https://doi.org/10.1007/978-3-662-26811-7_9
Download citation
DOI: https://doi.org/10.1007/978-3-662-26811-7_9
Publisher Name: Physica, Heidelberg
Print ISBN: 978-3-662-26813-1
Online ISBN: 978-3-662-26811-7
eBook Packages: Springer Book Archive