Estimating Multivariate Latent-Structure Models - Archive ouverte HAL Access content directly
Journal Articles Annals of Statistics Year : 2016

Estimating Multivariate Latent-Structure Models


A constructive proof of identification of multilinear decompositions of multiway arrays is presented. It can be applied to show identification in a variety of multivariate latent structures. Examples are finite-mixture models and hidden Markov models. The key step to show identification is the joint diagonalization of a set of matrices in the same non-orthogonal basis. An estimator of the latent-structure model may then be based on a sample version of this joint-diagonalization problem. Algorithms are available for computation and we derive distribution theory. We further develop asymptotic theory for orthogonal-series estimators of component densities in mixture models and emission densities in hidden Markov models.
Fichier principal
Vignette du fichier
2016-bonhomme-jochmans-robin-estimating-multivariate-latent-structure-models.pdf (479.1 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03392022 , version 1 (21-10-2021)



Stéphane Bonhomme, Koen Jochmans, Jean-Marc Robin. Estimating Multivariate Latent-Structure Models. Annals of Statistics, 2016, 44 (2), pp.540 - 563. ⟨10.1214/15-AOS1376⟩. ⟨hal-03392022⟩
5 View
16 Download



Gmail Facebook Twitter LinkedIn More