BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4//
BEGIN:VEVENT
UID:20250511T050252EDT-1855uBhkbz@132.216.98.100
DTSTAMP:20250511T090252Z
DESCRIPTION:Sebastien Haneuse\, PhD\n\nProfessor of Biostatistics | Harvard
  T.H. Chan School of Public Health\n\nWHEN: Wednesday\, November 8\, 2023\
 , from 3:30-4:30 p.m.\n\nWHERE: Hybrid | 2001 51³Ô¹ÏÍøCollege\, Rm 1140 | Z
 oom &\n\nNote: Dr. Haneuse will present in-person\n\nAbstract\n\nMissing d
 ata are ubiquitous in electronic health records-based comparative effectiv
 eness research. When data are informatively missing (or missing not at ran
 dom)\, however\, standard methods cannot be relied upon to guarantee valid
  estimation and inference. In such settings\, double-sampling facilitates 
 the collection of additional data which\, coupled with appropriate assumpt
 ions\, may provide a means to perform valid causal inference. In this work
  we present recent methodologic developments on the use of double sampling
  towards estimation and inference regarding causal average treatment effec
 ts and weighted quantile treatment effects. The work is motivated by and i
 llustrated with an EHR-based study of long-term outcomes following bariatr
 ic surgery.\n\nSpeaker Bio\n\nDr. Haneuse is a Professor of Biostatistics 
 and Director of Graduate Studies\, overseeing the PhD program at Harvard T
 .H. Chan School of Public Health. He is an AE for Biometrics\, and Statist
 ical Editor for JAMA Network Open.\n	For more information please visit: htt
 ps://www.hsph.harvard.edu/profile/sebastien-haneuse/ \n\n \n
DTSTART:20231108T203000Z
DTEND:20231108T210000Z
SUMMARY:Double sampling for informatively missing data in EHR-based compara
 tive effectiveness research
URL:/epi-biostat-occh/channels/event/double-sampling-i
 nformatively-missing-data-ehr-based-comparative-effectiveness-research-352
 447
END:VEVENT
END:VCALENDAR