Central bank research hub - Papers by Robert Kohn
https://www.bis.org/cbhub/list/author/author_4804/index.rss
Research hub papers by author Robert KohnenModeling Conditional Densities Using Finite Smooth Mixtures
http://www.riksbank.com/upload/Dokument_riksbank/Kat_publicerat/WorkingPapers/2010/wp245.pdf
Sveriges Riksbank Working Papers by Feng Li, Mattias Villani and Robert KohnModeling Conditional Densities Using Finite Smooth Mixtures2010-09-29T17:38:59ZSmooth 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.Modeling Conditional Densities Using Finite Smooth MixturesAbstracthttp://www.riksbank.com/templates/Page.aspx?id=45006Full texthttp://www.riksbank.com/upload/Dokument_riksbank/Kat_publicerat/WorkingPapers/2010/wp245.pdfRobert KohnFeng LiMattias VillaniFeng Li, Mattias Villani and Robert Kohn2010-09-29Sveriges Riksbank Working PapersFlexible Modeling of Conditional Distributions Using Smooth Mixtures of Asymmetric Student T Densities
http://www.riksbank.com/upload/Dokument_riksbank/Kat_publicerat/WorkingPapers/2009/wp233.pdf
Sveriges Riksbank Working Papers by Feng Li, Mattias Villani and Robert KohnFlexible Modeling of Conditional Distributions Using Smooth Mixtures of Asymmetric Student T Densities2009-11-09T12:39:59ZA 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 components, the mean, degrees of freedom, scale and skewness, are all modelled as functions of the covariates. Inference is Bayesian and the computation is carried out using Markov chain Monte Carlo simulation. To enable model parsimony, a variable selection prior is used in each set of covariates and among the covariates in the mixing weights. The model is used to analyse the distribution of daily stock market returns, and shown to more accurately forecast the distribution of returns than other widely used models for financial data.Flexible Modeling of Conditional Distributions Using Smooth Mixtures of Asymmetric Student T DensitiesAbstracthttp://www.riksbank.com/templates/Page.aspx?id=42499Full texthttp://www.riksbank.com/upload/Dokument_riksbank/Kat_publicerat/WorkingPapers/2009/wp233.pdfRobert KohnFeng LiMattias VillaniFeng Li, Mattias Villani and Robert Kohn2009-11-09Sveriges Riksbank Working PapersNonparametric Regression Density Estimation Using a Mixture of Adaptive Heteroscedastic Experts
http://www.riksbank.se/upload/Dokument_riksbank/Kat_publicerat/WorkingPapers/2007/wp211.pdf
Sveriges Riksbank Working Papers by Mattias Villani , Robert Kohn and Paolo GiordaniNonparametric Regression Density Estimation Using a Mixture of Adaptive Heteroscedastic Experts2007-10-04T17:38:00ZNonparametric Regression Density Estimation Using a Mixture of Adaptive Heteroscedastic ExpertsAbstracthttp://www.riksbank.se/templates/Page.aspx?id=25843Full texthttp://www.riksbank.se/upload/Dokument_riksbank/Kat_publicerat/WorkingPapers/2007/wp211.pdfRobert KohnPaolo GiordaniMattias VillaniMattias Villani , Robert Kohn and Paolo Giordani2007-10-04Sveriges Riksbank Working PapersEfficient Bayesian Inference for Multiple Change-Point and Mixture Innovation Models
http://www.riksbank.se/upload/Dokument_riksbank/Kat_publicerat/WorkingPapers/wp_196.pdf
Sveriges Riksbank Working Papers by Paolo Giordani and Robert KohnEfficient Bayesian Inference for Multiple Change-Point and Mixture Innovation Models2006-06-01T12:00:00ZEfficient Bayesian Inference for Multiple Change-Point and Mixture Innovation ModelsAbstracthttp://www.riksbank.se/templates/Page.aspx?id=21616Full texthttp://www.riksbank.se/upload/Dokument_riksbank/Kat_publicerat/WorkingPapers/wp_196.pdfRobert KohnPaolo GiordaniPaolo Giordani and Robert Kohn2006-05-24Sveriges Riksbank Working PapersC11C15C22