BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4//
BEGIN:VEVENT
UID:20260729T022913EDT-7973UKrSJf@132.216.98.100
DTSTAMP:20260729T062913Z
DESCRIPTION:Mohammad Ehsanul Karim\, PhD\n\nPostdoctoral Researcher\, Epide
 miology\, Biostatistics and Occupational Health\, McGill University\n\nCom
 parison of Statistical Approaches Dealing with Immortal Time Bias in Drug 
 Effectiveness Studies\n\nJoint work with: Paul Gustafson\, John Petkau\, H
 elen Tremlett\, and The BeAMS study group (UBC)\n\nALL ARE WELCOME\n\nAbst
 ract:\n\nIn time-to-event analyses of observational studies of drug effect
 iveness\, incorrect handling of the period between cohort entry and first 
 treatment exposure during follow-up may result in immortal time bias. This
  bias can be eliminated by acknowledging a change in treatment exposure st
 atus with time-dependent analyses\, such as fitting a time-dependent Cox m
 odel. The prescription time-distribution matching (PTDM) method has been p
 roposed as a simpler approach for controlling immortal time bias. In addit
 ion\, the performance of PTDM approach has been shown to be similar to the
  time-dependent Cox model in an epidemiologic application. Using simulatio
 n studies and theoretical quantification of bias\, we compared the perform
 ance of PTDM approach with that of the time-dependent Cox model in the pre
 sence of immortal time. Both assessments revealed that the PTDM approach d
 id not adequately address immortal time bias. Based on our simulation resu
 lts\, the sequential Cox approach\, another recently proposed observationa
 l data analysis technique\, was found to be more useful than the PTDM appr
 oach (Bias: -0.002\, MSE: 0.025 versus PTDM Bias: -1.411  MSE: 2.011 in th
 e main simulation). These approaches were applied to investigate the impac
 t of beta-interferon treatment in delaying disability progression in the B
 ritish Columbia Multiple Sclerosis cohort (1995 - 2008).\n\nBio:\n\nwww.st
 at.ubc.ca/~e.karim\n\n \n
DTSTART:20160119T203000Z
DTEND:20160119T213000Z
LOCATION:Room 24\, Purvis Hall\, CA\, QC\, Montreal\, H3A 1A2\, 1020 avenue
  des Pins Ouest
SUMMARY:Biostatistics Seminar
URL:https://www.mcgill.ca/epi-biostat-occh/channels/event/biostatistics-sem
 inar-257494
END:VEVENT
END:VCALENDAR