<?xml version="1.0" encoding="UTF-8"?><xml><records><record><source-app name="Biblio" version="7.x">Drupal-Biblio</source-app><ref-type>5</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Feng Li</style></author><author><style face="normal" font="default" size="100%">Villani, Mattias</style></author><author><style face="normal" font="default" size="100%">Kohn, Robert</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">Modelling Conditional Densities Using Finite Smooth Mixtures</style></title><secondary-title><style face="normal" font="default" size="100%">Mixtures: Estimation and Applications</style></secondary-title></titles><keywords><keyword><style  face="normal" font="default" size="100%">capable of approximating - large class of conditional distributions</style></keyword><keyword><style  face="normal" font="default" size="100%">finite smooth mixtures</style></keyword><keyword><style  face="normal" font="default" size="100%">first real dataset - using laser-emitted light to detect chemical compounds in atmosphere</style></keyword><keyword><style  face="normal" font="default" size="100%">generalised linear model (GLM) - to variable selection case</style></keyword><keyword><style  face="normal" font="default" size="100%">inference methodology - general MCMC scheme</style></keyword><keyword><style  face="normal" font="default" size="100%">LIDAR data</style></keyword><keyword><style  face="normal" font="default" size="100%">log predictive density score (LPDS)</style></keyword><keyword><style  face="normal" font="default" size="100%">model comparison - components assumed known in MCMC scheme</style></keyword><keyword><style  face="normal" font="default" size="100%">modelling conditional densities - using finite smooth mixtures</style></keyword><keyword><style  face="normal" font="default" size="100%">or mixtures of experts (ME) - knowing machine learning literature</style></keyword><keyword><style  face="normal" font="default" size="100%">simple-and-many versus complex-and-few - modelling regression data-skewed response variable</style></keyword><keyword><style  face="normal" font="default" size="100%">simulation study in Villani et al. (2009) - smooth mixture of homoscedastic Gaussian components for heteroscedastic data</style></keyword><keyword><style  face="normal" font="default" size="100%">smooth mixtures</style></keyword></keywords><dates><year><style  face="normal" font="default" size="100%">2011</style></year></dates><urls><web-urls><url><style face="normal" font="default" size="100%">https://archive.riksbank.se/en/Web-archive/Published/Other-reports/Working-Paper-Series/2010/No-245-Modeling-Conditional-Densities-Using-Finite-Smooth-Mixtures/index.html</style></url></web-urls></urls><publisher><style face="normal" font="default" size="100%">John Wiley &amp;amp;amp; Sons</style></publisher><pages><style face="normal" font="default" size="100%">123–144</style></pages><isbn><style face="normal" font="default" size="100%">978-1-119-99567-8</style></isbn><language><style face="normal" font="default" size="100%">eng</style></language><abstract><style face="normal" font="default" size="100%">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 number of components. This paper explores how well a smooth mixture of symmetric components can capture skewed data. Simulations and applications on real data show that including covariate-dependent skewness in the components can lead to substantially improved performance on skewed data, often using a much smaller number of components. Furthermore, variable selection is effective in removing unnecessary covariates in the skewness, which means that there is little loss in allowing for skewness in the components when the data are actually symmetric. We also introduce smooth mixtures of gamma and log-normal components to model positively-valued response variables.</style></abstract></record></records></xml>