BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Date iCal//NONSGML kigkonsult.se iCalcreator 2.20.2//
METHOD:PUBLISH
BEGIN:VTIMEZONE
TZID:America/Chicago
BEGIN:STANDARD
DTSTART:20221106T020000
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
TZNAME:CST
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20230312T020000
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
TZNAME:CDT
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:calendar.25715.field_event_date_2.0@math.wustl.edu
CREATED:20230112T204121Z
DESCRIPTION:Abstract: Networks are an increasingly common data structure,
and their growing popularity demands the development of new statistical me
thodology. In this talk I'll discuss several projects motivated by applica
tions in human neuroimaging that develop statistical tools for analyzing a
sample of networks and associated unit-level covariates. In this setting\
, a unit of observation is a person, unit-level covariates contain inform
ation such as demographics, diagnoses, etc., and a signed, weighted ne
twork represents functional connectivity. All networks are observed on a c
ommon node set, corresponding to one of the known brain atlases. Like man
y networks encountered in practice, brain connectivity networks exhibit m
arked community structure, and this can be exploited to improve interpret
ability when conducting modeling and inference.\n\nI will first briefly di
scuss the challenge of characterizing the distribution of a network given
a unit-level covariate as well as the converse problem of predicting a uni
t-level covariate given a network. The rest of the talk will focus on the
setting with multiple unit-level covariates. In our motivating application
, these are scores obtained from a battery of behavioral assessments. A u
seful tool in this setting is Canonical Correlation Analysis (CCA), a met
hod for analyzing two sets of variables. CCA learns a sequence of linear t
ransformations (canonical directions) to obtain new variables that are max
imally correlated with one another. CCA has seen a resurgence of popularit
y with applications including brain imaging and genomics where the goal is
often to identify relationships between high-dimensional data such as con
nectivity with more moderately sized phenotypic measurements. Inference in
CCA applications is typically limited to testing whether the transformed
variables are correlated, whereas inference for the canonical directions
has received comparatively little attention. I will present several propos
ed approaches for conducting inference on canonical directions obtained by
CCA and illustrate them on both synthetic data and data from the Adolesce
nt Brain Cognitive Development (ABCD) study.\n\nHost: Robert Lunde\n\nTea
will be available at 3:30pm in room 200.
DTSTART;TZID=America/Chicago:20230126T160000
DTEND;TZID=America/Chicago:20230126T170000
LAST-MODIFIED:20230112T204121Z
SUMMARY:Colloquium: 'Statistical Tools for Inference on Samples of Networks
with Applications to Neuroimaging'
URL;TYPE=URI:https://math.wustl.edu/events/colloquium-statistical-tools-inf
erence-samples-networks-applications-neuroimaging
END:VEVENT
END:VCALENDAR