BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4//
BEGIN:VEVENT
UID:20260919T233509EDT-0925a4jJ82@132.216.98.100
DTSTAMP:20260920T033509Z
DESCRIPTION:Title: 'Uncover Hidden Fine-Grained Scientific Information: Str
 uctured Latent Attribute Models'\n\nAbstract: In modern psychological and 
 biomedical research with diagnostic purposes\, scientists often formulate 
 the key task as inferring the fine-grained latent information under struct
 ural constraints. These structural constraints usually come from the domai
 n experts’ prior knowledge or insight. The emerging family of Structured L
 atent Attribute Models (SLAMs) accommodate these modeling needs and have r
 eceived substantial attention in psychology\, education\, and epidemiology
 . SLAMs bring exciting opportunities and unique challenges. In particular\
 , with high-dimensional discrete latent attributes and structural constrai
 nts encoded by a design matrix\, one needs to balance the gain in the mode
 l’s explanatory power and interpretability\, against the difficulty of und
 erstanding and handling the complex model structure.\n\nIn the first part 
 of this talk\, I present identifiability results that advance the theoreti
 cal knowledge of how the design matrix influences the estimability of SLAM
 s. The new identifiability conditions guide real-world practices of design
 ing diagnostic tests and also lay the foundation for drawing valid statist
 ical conclusions. In the second part\, I introduce a statistically consist
 ent penalized likelihood approach to selecting significant latent patterns
  in the population. I also propose a scalable computational method. These 
 developments explore an exponentially large model space involving many dis
 crete latent variables\, and they address the estimation and computation c
 hallenges of high-dimensional SLAMs arising from large-scale scientific me
 asurements. The application of the proposed methodology to the data from a
 n international educational assessment reveals meaningful knowledge struct
 ure of the student population.\n
DTSTART:20200106T213000Z
DTEND:20200106T223000Z
LOCATION:Room 1104\, Burnside Hall\, CA\, QC\, Montreal\, H3A 0B9\, 805 rue
  Sherbrooke Ouest
SUMMARY:Yuqi Gu (University of Michigan)
URL:https://www.mcgill.ca/mathstat/channels/event/yuqi-gu-university-michig
 an-303120
END:VEVENT
END:VCALENDAR