Handling large number of observation units in three-way methods for the analysis of qualitative and quantitative two-way data (Q1965944)

The authors propose short cut algorithms for INDSCAL, IDIOSCAL and TUCKALS-3 applied to quantification matrices. The proposed variants of these algorithms can handle large numbers of objects in the case where quantification matrices are of rank much smaller than the number of objects. It is shown that results of three-way methods at hand are essentially based only on certain aggregate measures for the variables like variances and covariances for numerical variables, and bivariate and marginal frequencies for nominal variables.