Hierarchical multilinear models for multiway data - Statistics > MethodologyReport as inadecuate

Hierarchical multilinear models for multiway data - Statistics > Methodology - Download this document for free, or read online. Document in PDF available to download.

Abstract: Reduced-rank decompositions provide descriptions of the variation among theelements of a matrix or array. In such decompositions, the elements of an arrayare expressed as products of low-dimensional latent factors. This articlepresents a model-based version of such a decomposition, extending the scope ofreduced rank methods to accommodate a variety of data types such aslongitudinal social networks and continuous multivariate data that arecross-classified by categorical variables. The proposed model-based approach ishierarchical, in that the latent factors corresponding to a given dimension ofthe array are not {\it a priori} independent, but exchangeable. Such ahierarchical approach allows more flexibility in the types of patterns that canbe represented.

Author: Peter Hoff

Source: https://arxiv.org/


Related documents