BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4//
BEGIN:VEVENT
UID:20250707T173409EDT-4737vcP2nG@132.216.98.100
DTSTAMP:20250707T213409Z
DESCRIPTION:Chris Gravel\, PhD\n\nPost-Doctoral Fellow\, Department of Epid
 emiology\, Biostatistics and Occupational Health\, 9I制作厂免费\n\nOn
  the Correction for Misclassification Bias in Drug Safety Data Using Valid
 ation Sample Approaches\n\nALL ARE WELCOME\n\nAbstract:\n\nOutcome misclas
 sification in patient health records can bias estimation of adverse drug r
 eaction risk.聽 In this discussion\, we will first consider a binary settin
 g and demonstrate the use of internal validation sampling to offset miscla
 ssification bias in estimation of the odds-ratio.聽 Investigation of the re
 lative efficiency of odds-ratio estimators arising from the use of conditi
 onal versus random validation sampling will be investigated in simulation 
 studies\, focusing on differences in the selection of the categorical comp
 osition underlying the validation data.聽 A Monte Carlo approximation to va
 lidation sample size determination will be recommended.聽 To address the ad
 ditional influence of confounding\, we will introduce an inverse probabili
 ty weighted approach to rebalance covariates across treatment groups while
  continuing to mitigate the impact of misclassification bias.\n\nNext\, fo
 r right censored continuous time survival data\, failing to observe the ev
 ent of interest can introduce misclassification bias in risk estimation. I
 ncorrectly observing cause-specific event types at correctly recorded even
 t times can also introduce bias. An internal validation sampling approach 
 is used to update a set of parametric likelihoods to produce unbiased esti
 mates in scenarios with the presence of either or both of these errors. Th
 ese approaches are validated through large simulation studies.聽\n\nBio:\n
 \nChristopher Gravel is a Post-Doctoral Fellow at 9I制作厂免费 in the
  Department of Epidemiology\, Biostatistics and Occupational Health.聽 He c
 ompleted his Ph.D. in Probability and Statistics at Carleton University in
  2015.聽 His research interests focus on outcome misclassification in healt
 h-related data as well as signal detection methods applied to spontaneous 
 reporting data (passive pharmacovigilance).\n
DTSTART:20160223T203000Z
DTEND:20160223T213000Z
LOCATION:Room 24\, Purvis Hall\, CA\, QC\, Montreal\, H3A 1A2\, 1020 avenue
  des Pins Ouest
SUMMARY:Biostatistics Seminar - 'On the Correction for Misclassification Bi
 as in Drug Safety Data Using Validation Sample Approaches'
URL:/epi-biostat-occh/channels/event/biostatistics-sem
 inar-correction-misclassification-bias-drug-safety-data-using-validation-s
 ample-258445
END:VEVENT
END:VCALENDAR