BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4//
BEGIN:VEVENT
UID:20250702T075934EDT-836849hsZi@132.216.98.100
DTSTAMP:20250702T115934Z
DESCRIPTION:Title: Propensity Score Weighting Analysis of Survival Outcomes
  Using Pseudo-observations.\n\nDr. Fan Li is an assistant professor in the
  Department of Biostatistics at Yale University School of Public Health. H
 e is also faculty member at the Center for Methods in Implementation and P
 revention Science (CMIPS) and the Yale Center for Analytical Sciences (YCA
 S). Dr. Li receives his PhD in Biostatistics from Duke University in 2019.
  His research interests include developing methods for comparative effecti
 veness research with randomized trials and observational studies. He is al
 so an expert in the design\, monitoring and analysis of pragmatic cluster 
 randomized trials\, and is currently Principal Investigator of a Patient-C
 entered Outcome Research Institute (PCORI) methods award “New methods for 
 planning cluster randomized trials to detect treatment effect heterogeneit
 y”. Website: https://ysph.yale.edu/profile/fan_f_li/\n\n\nSurvival outcome
 s are common in comparative effectiveness studies. A standard approach for
  causal inference with survival outcomes is to fit a Cox proportional haza
 rds model to an inverse probability weighted (IPW) sample. However\, this 
 method can be subject to model misspecification and the resulting hazard r
 atio estimate lacks causal interpretation. Moreover\, IPW often correspond
 s to an inappropriate target population when there is lack of covariate ov
 erlap between the treatment groups. To address these limitations\, we prop
 ose a general class of model-free causal estimands with survival outcomes 
 on user-specified target populations\, and develop a class of propensity s
 core weighting estimators via the pseudo-observation approach. As the pseu
 do-observations are constructed by jackknifing\, re-sampling-based inferen
 ce are generally computationally intensive. To circumvent the computationa
 l intensity\, we develop new asymptotic variance expressions for the class
  of weighting estimators based on the functional delta-method and von Mise
 s expansion of pseudo-observations. We show that the overlap weights devel
 oped for non-censored outcomes still lead to the most asymptotically effic
 ient causal comparisons based on pseudo-observations\, expanding the theor
 etical underpinnings of overlap weights. Extensive simulations are carried
  out to examine the operating characteristics of the weighting estimators 
 based on pseudo-observations. Finally\, we apply the proposed methods to s
 tudy the treatment effect of radiotherapeutic or surgical approaches for p
 atient with high-risk localized prostate cancer.\n\n \n\nSeminar Epidemiol
 ogy\, Biostatistics\, & Occupational Health\n	Via Zoom: https://mcgill.zoom
 .us/j/85978187693?pwdV=WWtJZUpnb0JXK3o5SStnOFcxK3FFUT09\n\nWeb site : www.
 mcgill.ca/epi-biostat-occh/news-events/seminars/biostatistics\n
DTSTART:20211124T203000Z
DTEND:20211124T213000Z
SUMMARY:Fan Li (Yale University School of Public Health)
URL:/mathstat/channels/event/fan-li-yale-university-sc
 hool-public-health-334663
END:VEVENT
END:VCALENDAR