Scientific Program and Schedule
September 5, 2016
| 18.00-19.00 | Registration |
| 19.00-19.30 | Opening |
| 19.30-21.00 | Welcome Cocktail |
September 6, 2016
08.00-08.30 Registration
08.30-09.25 Keynote Lecture 1
Richard Samworth (UK)
Random projection ensemble classification
Chair: Angela Montanari
09.25-10.50 Talk Session 1
Robust estimation in model-based clustering
Chair: Christian Hennig
Finding the Number of Groups in Model-Based Clustering via Constrained Likelihoods
Recent results on robust estimation of mixtures
Robust estimation and clustering of noisy regression mixtures
10.50-11.20 Coffee Break
11.20-12.45 Talk Session 2
Recent advances in mixture models for censored data
Chair: Víctor H. Lachos Dávila
Robust Regression Modeling for Censored Data based on Mixtures of Student-t Distributions
Model-based clustering for high-dimensional regression data
Bayesian semiparametric modeling for HIV longitudinal data with censoring and skewness
12.45-13.05 Lightning Talk Session 1
Chair: Roberto Di Mari
Joint models for longitudinal and survival data: comparison between AR(1) and RIS formulation for the random effects
Looking for the determinants of heterogeneity in education returns’ estimation: a semi-parametric approach
Studying the contribution of variables to the classification of individual observations
Cluster Weighted Models for Count Data
Hospital differences in caesarean deliveries in Sardinia: case-mix or something more? A Bayesian non-parametric approach
Inverse clustering: exploring the space of clustering parameters to match the model data
13.05-14.05 Lunch
14.05-15.30 Talk Session 3
Data Clustering
Chair: Sugnet Lubbe
What does ICL tell us about homogeneity for Model-Based Clustering?
Covariance matrix constraints in model-based clustering
Learning a frontier: some developments in one-class classification
15.30-16.25 Keynote Lecture 2
Christophe Biernacki (France)
Unifying Data Units and Models in Statistics
Chair: Agustin Mayo-Iscar
16.25-16.55 Coffee Break
16.55-18.20 Talk Session 4
Issues in mixture models
Chair: Brendan Murphy
A Probabilistic Distance Algorithm for Gaussian Mixture Parameter Estimation
An effective strategy for initializing the EM algorithm in finite mixture models
On Manly mixture modeling with extensions
18.20-18.45 Lightning Talk Session 2
Chair: Yana Melnikov
Mixture growth modeling of households’ investment in risky financial assets
Finite mixture of linear regression models: an adaptive constrained approach to maximum likelihood estimation
Satble and Non Stable Clustering Models
A pivotal relabelling solution for label switching problem in Bayesian finite mixture models
Mixture of vine copulas for clustering
Assessing the TCLUST methodology for robust clusterwise linear regression data
20.30 Workshop Dinner
September 7, 2016
8.45-9.40 Keynote Lecture 3
David Hunter (USA)
Clustering via Nonparametric Mixture Models
Chair: Maurizio Vichi
9.40-10.35 Keynote Lecture 4
Marco Alfò (Italy)
On finite mixtures of regression models for longitudinal data
Chair: Gilles Celeux
10.35-11.05 Coffee Break
11.05-12.30 Talk Session 5
Recent advances for finite mixtures
Chair: Sylvia Frühwirth-Schnatter
Latent Space Stochastic Block Model for Social Networks
Some recent advances for Sparse Finite Mixtures
Choosing mixture components via non-local priors
12.30-12.50 Lightning Talk Session 3
Chair: Aghiles Salah
High definition customers. How to get more value from your market segmentation
Symbolic Data Analysis for Disease Prognosis with SNP data
Model Based- Time Series Anomaly Detection using Constrained Clustering
Evaluation of predictive clustering quality
The flexible space-time model
CUB model trees for ordinal response: preliminary results
12.50-13.50 Lunch
13.50-15.15 Talk Session 6
Modeling high-dimensional and sparse data
Chair: Volodymyr Melnikov
Fitting Mixture Models to Large Data Sets
Model-based Clustering with Sparse Covariance Matrices
Model-based von Mises-Fisher Co-clustering
15.15-16.10 Keynote Lecture 5
Christian Hennig (UK)
Gaussian and not-so-Gaussian clustering with robustness against outliers and a stab at the number of clusters
Chair: Geoff McLachlan
16.10-17.10 Poster Session with Coffee Break
17.10-18.35 Talk Session 7
Models for mixted-type, ordinal and network data
Chair: Tae Rim Lee
A mixture model for mixed-type data: a case study
Mixture-based Clustering for Ordinal Data
Dynamic Stochastic Blockmodels for network data: a composite likelihood approach
18.35-18.40 Closing
18.40-19.45 Wine Session
Chair: Mariella Ferrara (Destro,
Masseria Setteporte,
Nicosia,
Tenuta Monte Gorna, Vivera)