We propose a latent Gaussian mixture model to classify ordinal data. The observed data are considered as a discretization of an underlying latent mixture. A pairwise likelihood approach is used to evaluate a multidimensional integral that cannot be written in a closed form. The model is estimated within the expectationmaximization framework.
Mixture models for ordinal data: a pairwise likelihood approach / Ranalli, Monia; Rocci, Roberto. - (2013), pp. 396-399. (Intervento presentato al convegno 9th Meeting of the Classification and Data Analysis Group tenutosi a Modena).
Mixture models for ordinal data: a pairwise likelihood approach
RANALLI, MONIA
Primo
;roberto Rocci
2013
Abstract
We propose a latent Gaussian mixture model to classify ordinal data. The observed data are considered as a discretization of an underlying latent mixture. A pairwise likelihood approach is used to evaluate a multidimensional integral that cannot be written in a closed form. The model is estimated within the expectationmaximization framework.File allegati a questo prodotto
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
