BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4//
BEGIN:VEVENT
UID:20250708T093252EDT-7757bKouTe@132.216.98.100
DTSTAMP:20250708T133252Z
DESCRIPTION:Title: Spatial Confounding and Restricted Spatial Regression Me
 thods.\n\nAbstract: Catherine (Kate) Calder is Professor of Statistics & D
 ata Sciences at the University of Texas at Austin. She joined the UT facul
 ty in 2019 and currently serves as Chair of the Department of Statistics &
  Data Sciences. Previously\, she spent 16 years on the faculty at The Ohio
  State University\, where she was Associate Director (2015–2018) and Co-Di
 rector (2018–2019) of the Mathematical Biosciences Institute. She is curre
 ntly an associate editor for the Annals of Applied Statistics and Bayesian
  Analysis and has served the profession through various elected roles in t
 he American Statistical Association (ASA) and in the International Society
  for Bayesian Analysis. Her research has been funded by the NIH\, NSF\, NA
 SA\, and other agencies and foundations. She received the ASA Section on S
 tatistics and the Environment’s 2013 Young Investigator Award and was elec
 ted Fellow of the ASA in 2014. Dr. Calder's current research focuses on sp
 atial statistics\, Bayesian methods\, and network analysis. Her work is mo
 tivated by applications in the environmental\, social\, and health science
 s.\n\n\nOver the last fifteen years\, spatial confounding has emerged as a
  significant source of concern when interpretable inferences on regression
  coefficients is a primary goal in a spatial regression analysis. Numerous
  approaches to alleviate spatial confounding have been proposed in the lit
 erature\, many of which have close connections to dimension reduction tech
 niques used for facilitating faster model fitting. In this presentation\, 
 I discuss the issue of spatial confounding in the context of the spatial g
 eneralized mixed model for areal data. In particular\, I show how many of 
 the techniques for dealing with spatial confounding in this setting can be
  viewed as a special case of what we refer to as restricted spatial regres
 sion (RSR) models. Theoretical characterizations of the posterior distribu
 tion of regression coefficients under the RSR model demonstrate that infer
 ences on coefficients can defy general expectations in the literature and 
 can produce inferences on regression coefficients that have counterintuiti
 ve relationships with their counterparts in non-spatial and non-RSR models
 . I will conclude with some general thoughts on restricted spatial regress
 ion and alternative approaches for quantifying causal effects in spatial a
 nalyses. This talk is based on joint work with Kori Khan\, Assistant Profe
 ssor of Statistics at Iowa State University.\n\nSeminar Epidemiology\, Bio
 statistics\, & Occupational Health\n	Via Zoom: https://mcgill.zoom.us/j/886
 25559031?pwd=NGxGSkU3bG9rZmRXTG82dFBNeXc3Zz09\n\n \n
DTSTART:20210324T193000Z
DTEND:20210324T203000Z
SUMMARY:Catherine (Kate) Calder (University of Texas at Austin)
URL:/mathstat/channels/event/catherine-kate-calder-uni
 versity-texas-austin-329599
END:VEVENT
END:VCALENDAR