BEGIN:VCALENDAR VERSION:2.0 PRODID:-//Date iCal//NONSGML kigkonsult.se iCalcreator 2.20.2// METHOD:PUBLISH BEGIN:VTIMEZONE TZID:America/New_York BEGIN:STANDARD DTSTART:20241103T020000 TZOFFSETFROM:-0400 TZOFFSETTO:-0500 TZNAME:EST END:STANDARD BEGIN:DAYLIGHT DTSTART:20250309T020000 TZOFFSETFROM:-0500 TZOFFSETTO:-0400 TZNAME:EDT END:DAYLIGHT END:VTIMEZONE BEGIN:VEVENT UID:calendar.3403.events_uoft_date.0@www.statistics.utoronto.ca CREATED:20240830T141220Z DESCRIPTION:\nWhen and Where: \nThursday, March 13, 2025 11:00 am to 12:0 0 pm \n\nSpeakers \nMichele Guindani \n\nDescription: \nThe critical role that statistical approaches play in analyzing brain imaging data will be f irst highlighted, particularly for functional magnetic resonance imaging (fMRI) data. Appropriate statistical methods are necessary to handle the c omplexity of spatial and temporal correlations typical of brain data. More specifically, we will discuss approaches to studying dynamic brain conne ctivity, which seeks to understand the changing interactions between diff erent brain regions over time. We will present novel Bayesian approaches t o capture these dynamic relationships within multivariate time series data .  In particular, we will present a scalable Bayesian time-varying tensor vector autoregressive (TV-VAR) model, aimed at efficiently capturing evo lving connectivity patterns.This model leverages a tensor decomposition of the VAR coefficient matrices at different lags and sparsity-inducing prio rs to capture dynamic connectivity patterns. If time allows, we will then discuss generalizations of the widely adopted psychophysiological interac tion (PPI) models in the neuroscience,  which estimates task-modulated ti me-varying background functional connectivity from an fMRI experiment. Thr oughout the talk, we will illustrate the performance of these Bayesian me thods with examples from simulation studies and real-world fMRI data.About  Michele GuindaniDr. Michele Guindani is a Professor in the Department of Biostatistics at the University of California, Los Angeles (UCLA). He ear ned his Ph.D. in Statistics from Università Bocconi in Milan, Italy, und er the guidance of Sonia Petrone and Alan E. Gelfand. Following his doctor ate, he completed a postdoctoral fellowship at the University of Texas MD Anderson Cancer Center under the guidance of Gary Rosner and Peter Muelle r. Before joining UCLA, Dr. Guindani held academic positions at the Unive rsity of New Mexico, the University of Texas MD Anderson Cancer Center, and the University of California, Irvine.His research focuses on Bayesian analysis, particularly Bayesian nonparametrics, with applications in ne uroimaging, integrative microbiome analysis, and radiomics. Dr. Guindani is a Fellow of both the American Statistical Association and the Internat ional Society for Bayesian Analysis, an elected member of the Internation al Statistical Institute, and a member of the Institute of Mathematical S tatistics. He currently serves as the 2025 President of the International Society for Bayesian Analysis. He is also past chair of the Section of Bay esian Statistical Sciences and current chair of the Section on Statistical Imaging of the ASA.In addition, Dr. Guindani has served as Editor-in-Chi ef of the journal 'Bayesian Analysis' from 2019 to 2021. He is a founding of co-Editor of the new ASA journal on 'Statistics and Data Science in Ima ging'. He is also an Associate Editor for Biometrics, Econometrics and St atistics, and the Journal of the American Statistical Association, Theor y and Methods. Dr. Guindani also serves as one of the the Chief Statistica l Advisor for Nature Medicine. \n\nCategories \n Seminar SeriesStatistics Colloquium \n\nAudiences \n FacultyGraduate Students DTSTART;TZID=America/New_York:20250313T110000 DTEND;TZID=America/New_York:20250313T120000 LAST-MODIFIED:20250310T122626Z SUMMARY:Bayesian Modeling in Neuroimaging: Brain Networks Dynamics URL;TYPE=URI:https://www.statistics.utoronto.ca/events/bayesian-modeling-ne uroimaging-brain-networks-dynamics END:VEVENT END:VCALENDAR