BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Manifold Data Analysis with Applications to High-Resolution 3D Ima
 ging - Matthew Reimherr (Pennsylvania State University)
DTSTART:20180320T100000Z
DTEND:20180320T110000Z
UID:TALK102655@talks.cam.ac.uk
CONTACT:INI IT
DESCRIPTION:Many scientific areas are faced with the challenge of extracti
 ng information from large\, complex\, and highly structured data sets. A g
 reat deal of modern statistical work focuses on developing tools for handl
 ing such data. In this work we presents a new subfield of functional data 
 analysis\, FDA\, which we call Manifold Data Analysis\, or MDA. MDA is con
 cerned with the statistical analysis of samples where one or more variable
 s measured on each unit is a manifold\, thus resulting in as many manifold
 s as we have units. We propose a framework that converts manifolds into fu
 nctional objects\, an efficient 2-step functional principal component meth
 od\, and a manifold-on-scalar regression model.  This work is motivated by
  an anthropological application involving 3D facial imaging data\, which i
 s discussed extensively throughout.  The proposed framework is used to und
 erstand how individual characteristics\, such as age and genetic ancestry\
 , influence the shape of the human face.
LOCATION:Seminar Room 1\, Newton Institute
END:VEVENT
END:VCALENDAR