News - Recently updated info


Sponsored by
Tutorials

Three independent tutorials will take place 11th to 13th December 2024 to the conference.

The tutorials are organized by the COST Action HiTEc (see HiTEc Winter Course 2024). The conference participants can register for each one of the tutorials separately. For further information send an email to info@CMStatistics.org.

Dates: 11-13 December 202.
Venue: Bush House, King's College London, UK. The sessions will take place in different rooms (see details in the programme below). For virtual access, see below.

Tutorial I (4 hours)

Regularization methods in statistics with an application to brain imaging studies.

Presenters: Jaroslaw (Jarek) Harezlak, Indiana University, USA.
Email: Contact

Dates: 11th December 2024 (morning, early afternoon).

Regularization methods play a crucial role in the analysis of brain imaging data, where the number of observations is frequently much smaller than the number of covariates. This is even more crucial in multi-modal imaging, where combining data from different sources (e.g., sMRI, fMRI, and dMRI) can enhance insights into brain structure and function. In these settings, regularization helps to address the challenges posed by high-dimensional, noisy data by imposing constraints that promote stability and interpretability in model estimation.

Off-the-shelf techniques such as Lasso, ridge regression, and elastic net are commonly employed to control overfitting and improve prediction accuracy, while spatial and informed regularization methods can leverage the inherent structure of imaging data, allowing for the integration of multiple imaging modalities. We describe the types of brain imaging data used, common regularization methods, and their extensions developed by us and others.

References

  1. Zou, Hui; Hastie, Trevor. Regularization and Variable Selection via the Elastic Net. Journal of the Royal Statistical Society, Series B. 67 (2) (2005): 301–320.
  2. T.W. Randolph, J. Harezlak, and Z. Feng, Structured penalties for functional linear models—partially empirical eigenvectors for regression, Electronic Journal of Statistics 6 (2012), 323–353.
  3. T. W. Randolph, Sen Zhao, Wade Copeland, Meredith Hullar, and Ali Shojaie, Kernel-penalized regression for analysis of microbiome data, The Annals of Applied Statistics 12 (2018), no. 1, 540–566.
  4. Marta Karas, Damian Brzyski, Mario Dzemidzic, Joaquin Goni, David A Kareken, Timothy W Randolph, and Jaroslaw Harezlak, Brain connectivity-informed regularization methods for regression, Statistics in Biosciences 11 (2019), 47–90.
  5. Damian Brzyski, Marta Karas, Beau M Ances, Mario Dzemidzic, Joaquin Goni, Timothy W Randolph, and Jaroslaw Harezlak, Connectivity-informed adaptive regularization for generalized outcomes, Canadian Journal of Statistics 49 (2021), no. 1, 203–227.
Tutorial II (13 hours)

Bayesian nonparametrics methods.

Presenters: Michele Guindani, UCLA, USA, and Francesco Denti, University of Padua, Italy.
Email: Contact

Dates: 11th December 2024 afternoon to 13th December 2024 morning.

This course provides a hands-on introduction to Bayesian Nonparametric methods, focusing on widely-used models like Dirichlet Processes and Pitman-Yor processes mixture modles. Through interactive sessions involving also coding exercises, participants will learn how to implement and apply these models using real-world data. The course also discusses more recent topics in Bayesian Nonparametrics, including hierarchical and nested nonparametric mixtures, mixtures of finite mixtures, and latest trends like biclustering and multi-view clustering for complex data structures.

Tutorial III (4 hours)

Robust modelling of volatility and other non-negative variables.

Presenters: Genaro Sucarrat, BI Norwegian Business School, Norway.
Email: Contact

Dates: 13th December 2024 afternoon.

Autoregressive Conditional Heteroscedasticity (ARCH) models can successfully be used to model uncertainty, volatility, and other non-negative variables (duration, volume, etc.). This tutorial provides a (biased) overview of robust models within the ARCH class, both univariate and multivariate versions (the latter via equation-by-equation methods).

Here, "robust" means that the estimation method is valid under density mis-specification, or that certain types of non-stationarities are allowed, or both. The models and methods covered have proved themselves very useful in applications, and are freely available in the statistical software R. The tutorial provides an overview of the models combined with practical exercises in R, thus enabling participants to get a hands-on experience in the implementation of the methods.

The instructor of the tutorial is Dr. Genaro Sucarrat (BI Norwegian Business School): https://www.sucarrat.net/

References

Programme

Wednesday, 11 December 2023

  • 09:30 - 11:00 Tutorial I (BH (NE)0.01)
  • 11:00 - 11:30 Coffee break
  • 11:30 - 12:30 Tutorial I (BH (NE)0.01)
  • 12:30 - 14:00 Lunch break
  • 14:00 - 15:30 Tutorial I (BH (NE)0.01)
  • 15:30 – 16:00 Coffee break
  • 16:00 – 18:00 Tutorial II (BH (NE)0.01)

Thursday, 12 December 2024

  • 09:00 - 10:30 Tutorial II (BH (S)2.01)
  • 10:30 - 11:00 Coffee break
  • 11:00 - 12:30 Tutorial II (BH (S)2.01)
  • 12:30 - 14:00 Lunch break
  • 14:00 - 16:00 Tutorial II (BH (SE)2.10)
  • 16:00 - 16:30 Coffee break
  • 16:30 – 18:30 Tutorial II (BH (SE)2.10)

Friday, 13 December 2024

  • 09:00 – 11:00 Tutorial II (BH (NE)-1.01)
  • 11:00 - 11:30 Coffee break
  • 11:30 - 13:30 Tutorial II (BH (NE)-1.01)
  • 13:30 - 15:00 Lunch break
  • 15:00 – 17:00 Tutorial III (BH (S)4.04)
  • 17:00 – 17:30 Coffee break
  • 17:30 – 19:30 Tutorial III (BH (S)4.04)

Instructions for virtual participants to access the tutorials
  1. Read the technical requirements and general information to enter the virtual room. Accessing the tutorials implies to accept the conditions.
  2. Log in to the registration tool to obtain the password. Only registered participants will have access.
  3. A Zoom link to join the tutorials will be provided here in due course.
  4. The conference staff will verify participants in the Zoom rooms. Ensure that you have entered the Zoom meeting with the same name and surname you used to register for the conference. Otherwise, rename yourself as soon as possible. Attendees not on the list of participants will be removed if they fail to identify themselves using the chat.
Organizers and sponsors

Organized by the HiTEc COST Action CA21163 with the collaboration of CFE-CMStatistics.

Sponsored by COST.

HiTEc Grants
PhD students and young researchers, according to the COST definition (under 40 years), from eligible COST countries* can apply for a limited number of grants. The granted participants will be reimbursed a daily allowance of 160 euros per day plus travel expenses of up to 350 euros.
  • In order to apply for the grants, candidates should submit their CV by e-mail to hiteccostaction@gmail.com.
  • Deadline for applications: 6th September 2024.
  • Granted candidates will be informed by e-mail after the deadline and must send their flight tickets and registration 7 days after the notification to secure their grants. Otherwise, their grants will be revoked and assigned to other candidate.
  • The granted candidates must attend all the sessions and sign the attendance list in order to obtain their grants.
*Eligible COST countries: Albania, Armenia, Austria, Belgium, Bosnia and Herzegovina, Bulgaria, Croatia, Cyprus, Czech Republic, Denmark, Estonia, Finland, France, Georgia, Germany, Greece, Hungary, Iceland, Ireland, Italy, Latvia, Lithuania, Luxembourg, Malta, the Republic of Moldova, Montenegro, The Netherlands, The Republic of North Macedonia, Norway, Poland, Portugal, Romania, Serbia, Slovakia, Slovenia, Spain, Sweden, Switzerland, Turkey, Ukraine, United Kingdom and Israel.
  • The granted candidates must attend all the sessions of the course in order to obtain their grants.