BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//talks.cam.ac.uk//v3//EN
BEGIN:VTIMEZONE
TZID:Europe/London
BEGIN:DAYLIGHT
TZOFFSETFROM:+0000
TZOFFSETTO:+0100
TZNAME:BST
DTSTART:19700329T010000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0100
TZOFFSETTO:+0000
TZNAME:GMT
DTSTART:19701025T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
CATEGORIES:Isaac Newton Institute Seminar Series
SUMMARY:Mining differential correlation - Andrew Nobel (Un
iversity of North Carolina )
DTSTART;TZID=Europe/London:20161215T093000
DTEND;TZID=Europe/London:20161215T103000
UID:TALK69511AThttp://talks.cam.ac.uk
URL:http://talks.cam.ac.uk/talk/index/69511
DESCRIPTION:Given data obtained under two sampling condi
tions\, it is often of interest to identify variab
les that behave differently in one condition than
in the other. The talk will describe a method for
differential analysis of second-order behavior cal
led Differential Correlation Mining (DCM). DCM is
a special case of differential analysis for weight
ed networks\, and is distinct from standard analys
es of first order differential behavior\, for exam
ple studies of differential expression.

T
he DCM method identifies differentially correlated
sets of variables\, with the property that the av
erage pairwise correlation between variables in a
set is higher under one sample condition than the
other. DCM is based on an iterative testing proced
ure that adaptively updates the size and elements
of a candidate variable set. Updates are performed
via hypothesis testing of individual variables\,
based on the asymptotic distribution of their aver
age differential correlation. The method does not
assume that the sample or population correlation m
atrices are sparse\, or have any particular struct
ure.

I will present both simulation resul
ts and applications of DCM to genomics and brain i
maging. \;As time permits\, I will also prese
nt a brief overview of some additional network rel
ated work being done with collaborators at UNC.

LOCATION:Seminar Room 1\, Newton Institute
CONTACT:info@newton.ac.uk
END:VEVENT
END:VCALENDAR