BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4//
BEGIN:VEVENT
UID:20260827T013659EDT-5779vVM9gk@132.216.98.100
DTSTAMP:20260827T053659Z
DESCRIPTION:Aurélie Labbe\, PhD\n\nAssistant Professor\, Departments of Epi
 demiology\, Biostatistics & Occupational Health and Psychiatry\, McGill Un
 iversity\n\nPrincipal component of explained variance\n\nALL ARE WELCOME\n
 \nAbstract:\n\nThe genomics era has led to an increase in the dimensionali
 ty of the data collected to investigate biological questions. In this cont
 ext\, dimension-reduction techniques can be used to summarize high-dimensi
 onal signals into low-dimensional ones\, to further test for association w
 ith one or more covariates of interest. We revisit one such approach\, pre
 viously known as Principal Component of Heritability and renamed here as P
 rincipal Component of Explained Variance (PCEV). As its name suggests\, th
 e PCEV seeks a linear combination of outcomes in an optimal manner\, by ma
 ximising the proportion of variance explained by one or several covariates
  of interest. By construction\, this\n\nmethod optimises power but limited
  by its computational complexity\, it has unfortunately received little at
 tention in the past. Here\, we propose a general analytical PCEV framework
  that builds on the assets of the original method\, i.e. conceptually simp
 le and free of tuning parameters. Moreover\, our framework extends the ran
 ge of applications of the original procedure by providing a computationall
 y simple strategy for high-dimensional outcomes\, along with exact and asy
 mptotic testing procedures that drastically reduce its computational cost.
  We investigate the merits of the\n\nPCEV using an extensive set of simula
 tions. Furthermore\, the use of the PCEV approach will be illustrated usin
 g three examples taken from the epigenetics and brain imaging areas.\n\nBi
 o:\n\nwww.medicine.mcgill.ca/epidemiology/labbe/\n\n \n\n \n
DTSTART:20160322T193000Z
DTEND:20160322T203000Z
LOCATION:Room 24\, Purvis Hall\, CA\, QC\, Montreal\, H3A 1A2\, 1020 avenue
  des Pins Ouest
SUMMARY:Biostatistics Seminar: 'Principal component of explained variance'
URL:https://www.mcgill.ca/epi-biostat-occh/channels/event/biostatistics-sem
 inar-principal-component-explained-variance-259540
END:VEVENT
END:VCALENDAR