BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//UM//UM*Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:America/Detroit
TZURL:http://tzurl.org/zoneinfo/America/Detroit
X-LIC-LOCATION:America/Detroit
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20070311T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20071104T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260303T101836
DTSTART;TZID=America/Detroit:20260320T120000
DTEND;TZID=America/Detroit:20260320T130000
SUMMARY:Presentation:Psychology Methods Hour: Prediction with intensive longitudinal data: Blending machine learning and mixed effects approaches
DESCRIPTION:This talk will cover a broad survey of methods for incorporating both group- and individual-level information in machine learning for intensive longitudinal data. The broad survey will be followed by a deep dive into mixed effects machine learning\, cluster-mean centering as a preprocessing step\, and results from an empirical study of momentary affect prediction with passive sensing data. The group may discuss further directions and unanswered questions\, use cases for this sort of work\, recommended frameworks and approaches for intensive longitudinal machine learning\, and how to incorporate cluster-mean centering into machine learning preprocessing.
UID:142543-21891137@events.umich.edu
URL:https://events.umich.edu/event/142543
CLASS:PUBLIC
STATUS:CONFIRMED
CATEGORIES:Psychology
LOCATION:East Hall - 4464
CONTACT:
END:VEVENT
END:VCALENDAR