DINDSCAL
swMATH ID:  13360 
Software Authors:  Trendafilov, Nickolay T. 
Description:  DINDSCAL: direct INDSCAL. The wellknown INDSCAL model for simultaneous metric multidimensional scaling (MDS) of threeway data analyzes doubly centered matrices of squared dissimilarities. An alternative approach, called for short DINDSCAL, is proposed for analyzing directly the input matrices of squared dissimilarities. An important consequence is that missing values can be easily handled. The DINDSCAL problem is solved by means of the projected gradient approach. First, the problem is transformed into a gradient dynamical system on a product matrix manifold (of Stiefel submanifold of zerosum matrices and nonnegative diagonal matrices). The constructed dynamical system can be numerically integrated which gives a globally convergent algorithm for solving the DINDSCAL. The DINDSCAL problem and its solution are illustrated by wellknown data routinely used in metric MDS and INDSCAL. Alternatively, the problem can also be solved by iterative algorithm based on the conjugate (projected) gradient method, which MATLAB implementation is enclosed as an appendix. 
Homepage:  http://link.springer.com/article/10.1007%2Fs1122201192352 
Dependencies:  Matlab 
Keywords:  threeway data; metric multidimensional scaling; missing values; dynamical system on matrix manifold; projected conjugate gradient 
Related Software:  ALSCAL; smacof; Matlab; fminbnd; KELLEY 
Cited in:  2 Publications 
Standard Articles
1 Publication describing the Software, including 1 Publication in zbMATH  Year 

DINDSCAL: direct INDSCAL. Zbl 1322.62159 Trendafilov, Nickolay T. 
2012

Cited by 4 Authors
1  GardnerLubbe, Sugnet 
1  Gower, John C. 
1  le Roux, Niël J. 
1  Trendafilov, Nickolay T. 
Cited in 2 Serials
1  Statistical Papers 
1  Statistics and Computing 
Cited in 3 Fields
2  Statistics (62XX) 
2  Numerical analysis (65XX) 
1  Game theory, economics, finance, and other social and behavioral sciences (91XX) 