Mixture Estimation and Applications

Home > Workshops > 2010 > Mixture Estimation and Applications

Mixture Estimation and Applications

 03 - 05 May 2010

ICMS

  • Kerrie Mengersen, Queensland University of Technology
  • Christian Robert, Université Paris-Dauphine & University of Warwick
  • Mike Titterington, University of Glasgow

About:

Statistical mixture distributions are used to model scenarios in which certain variables are measured but a categorical variable is missing. For example, although clinical data on a patient may be available their disease category may not be, and this adds significant degrees of complication to the statistical analysis. The above situation characterises the simplest mixture-type scenario; variations include, among others, hidden Markov models, in which the missing variable follows a Markov chain model, and latent structure models, in which the missing variable or variables represent model-enriching devices rather than real physical entities.

Speakers

Murray Aitkin, University of Melbourne - How Many Normal Components in the Galaxy Velocity Data? Posterior Deviance  Distributions for the Number of Components, and their Interpretation   

Clare Alston, Queensland University of Technology - Bayesian Mixture Models: a Blood Free Dissection of a Sheep 

Christophe Andrieu, University of Bristol - Exact Approximations of MCMC Algorithms

Olivier Cappé, Telecom ParisTech & CNRS - Online EM Algorithms for Mixtures, HMMs and Beyond  

Jiahua Chen, University of British Columbia - Testing the Order of Finite Mixture Models by EM-Test   

Kim-Anh Do, University of Texas  - Bayesian Mixture Modelling with Applications to Translational Cancer Research  

Paul Fearnhead, Lancaster University - Sequential Monte Carlo Methods and Perfect Sampling for Mixture Models 

Sylvia Fruehwirth-Schnatter, Johannes Kepler University Linz - Dealing with Label Switching Under Model Uncertainty  

Richard Gerlach, University of Sydney - Smooth Transition Mixture GARCH Models for Forecasting Risk Measures in Financial Markets   

John Geweke, University of Technology - Interpretation and Inference in Mixture Models  

Mark Girolami, University of Glasgow - Inferring Spectral Mixture Components in Multiplexed Surface Enhanced Raman Resonance Spectroscopy  

Katherine Heller, University of Cambridge - The IBP Compound Dirichlet Process and its Application to Focused Topic Modelling

Chris Holmes, University of Oxford - Investigations in Variable Selection for Bayesian Mixture Models   

Michael Jordan, University of California - Applied Bayesian Nonparametrics  

Michael Jordan, University of California - Completely Random Measures, Hierarchy and Nesting in Bayesian Nonparametrics

Robert Kohn, University of New South Wales - Bayesian Mixtures of Autoregressive Models   

Bruce Lindsay, Pennsylvania State University - Mixture Related Analysis in Many Dimensions  

Geoff McLachlan, University of Queensland - The Modelling of High-Dimensional Data via Normal Mixture Models  

Kerrie Mengersen, Queensland University of Technology - Where Are They and What Do They Look Like?  Discovering Patterns in Data Using Statistical Mixture Models 

Peter Müller, University of Texas - Bayesian Semiparametric Mixture Models with Covariate-Dependent Weights  

Iain Murray, University of Toronto & University of Edinburgh - Sampling Latent Variable Models

Brendan Murphy, University College Dublin - A Mixture of Experts Latent Position Cluster Model for Social Network Data

Michael Newton, University of Wisconsin - Gamma-Based Clustering via Ordered Means with Application to Gene-Expression Analysis

Yee Whye Teh, University College London - On Hierarchical Clustering, Partitions and Mixture Models

Chris Williams, University of Edinburgh - Greedy Learning of Binary Latent Trees

Sponsors and Funders:

Funded by the EPSRC, the LMS, the Edinburgh Mathematical Society, the Glasgow Mathematical Journal Trust and the Royal Statistical Society.