Search Results - subject:"Mixture of Experts"

Modeling conditional densities using finite smooth mixtures

Li, Feng; Villani, Mattias; Kohn, Robert - 2010

Smooth mixtures, i.e. mixture models with covariate-dependent mixing weights, are very useful flexible models for conditional densities. Previous work shows that using too simple mixture components for modeling heteroscedastic and/or heavy tailed data can give a poor fit, even with a large...

Persistent link: https://www.econbiz.de/10010320786

Bayesian Generalized Product Partition Model

Dunson, David - 2010

Starting with a carefully formulated Dirichlet process (DP) mixture model, we derive a generalized product partition model (GPPM) in which the partition process is predictor-dependent. The GPPM generalizes DP clustering to relax the exchangeability assumption through the incorporation of...

Persistent link: https://www.econbiz.de/10009475421

Clustering ranked preference data using sociodemographic covariates

Gormley, Isobel Claire; Murphy, Thomas Brendan - 2010

to model the population of judges, where each component in the mixture represents a group of judges. Mixture of experts … proportions and the component density parameters. A mixture of experts model for ranked preference data is developed by combining … a mixture of experts model and a mixture of Plackett-Luce models. Particular attention is given to the manner in which …

Persistent link: https://www.econbiz.de/10009475695

Modeling Conditional Densities Using Finite Smooth Mixtures

Li, Feng; Villani, Mattias; Kohn, Robert - Sveriges Riksbank - 2010

Persistent link: https://www.econbiz.de/10008671765

Flexible modeling of conditional distributions using smooth mixtures of asymmetric student T densities

Li, Feng; Villani, Mattias; Kohn, Robert - 2009

A general model is proposed for flexibly estimating the density of a continuous response variable conditional on a possibly high-dimensional set of covariates. The model is a finite mixture of asymmetric student-t densities with covariate dependent mixture weights. The four parameters of the...

Persistent link: https://www.econbiz.de/10010320729

Nonparametric Bayes Conditional Distribution Modeling With Variable Selection

Dunson, David - 2009

This article considers a methodology for flexibly characterizing the relationship between a response and multiple predictors. Goals are (1) to estimate the conditional response distribution addressing the distributional changes across the predictor space, and (2) to identify important predictors...

Persistent link: https://www.econbiz.de/10009475527

Flexible Modeling of Conditional Distributions Using Smooth Mixtures of Asymmetric Student T Densities

Li, Feng; Villani, Mattias; Kohn, Robert - Sveriges Riksbank - 2009

Persistent link: https://www.econbiz.de/10008469620

Nonparametric regression density estimation using smoothly varying normal mixtures

Villani, Mattias; Kohn, Robert; Giordani, Paolo - 2007

We model a regression density nonparametrically so that at each value of the covariates the density is a mixture of normals with the means, variances and mixture probabilities of the components changing smoothly as a function of the covariates. The model extends existing models in two important...

Persistent link: https://www.econbiz.de/10010320765

Nonparametric Regression Density Estimation Using Smoothly Varying Normal Mixtures

Villani, Mattias; Kohn, Robert; Giordani, Paolo - Sveriges Riksbank - 2007

We model a regression density nonparametrically so that at each value of the covariates the density is a mixture of normals with the means, variances and mixture probabilities of the com- ponents changing smoothly as a function of the covariates. The model extends existing models in two...

Persistent link: https://www.econbiz.de/10005649083

Dynamic learning in behavioral games: A hidden Markov mixture of experts approach

Ansari, Asim; Montoya, Ricardo; Netzer, Oded - In: Quantitative Marketing and Economics 10 (2012) 4, pp. 475-503

uncover the latent learning rules and learning paths used by the players. We build a non-homogeneous hidden Markov mixture of … experts model which captures shifts between different learning rules over the course of a repeated game. The transition …

Persistent link: https://www.econbiz.de/10010865232