BEGIN:VCALENDAR
PRODID:-//Columba Systems Ltd//NONSGML CPNG/SpringViewer/ICal Output/3.3-
 M3//EN
VERSION:2.0
CALSCALE:GREGORIAN
METHOD:PUBLISH
BEGIN:VEVENT
DTSTAMP:20180608T132722Z
DTSTART:20180611T130000Z
SUMMARY:Centre for Biostatistics Seminar
UID:{http://www.columbasystems.com/customers/uom/gpp/eventid/}c7q-ji609jn
 j-7t2m9q
DESCRIPTION:Title: Application/Applicability of Marginal Structural Model
 s (MSMs) to irregular healthcare data\n\nThe uptake of Marginal Structur
 al Models (MSMs) as a methodological alternative for causal inference pa
 rticularly when treatments are time varying and confounded by time varyi
 ng covariates has been increasing and continues to do so. This increase 
 in use of this methodological approach is attributed to its ability to g
 ive unbiased estimates when treatments are time varying and confounded b
 y time varying covariates. However\, MSMs have been widely used in clini
 cal settings where individuals are observed and have their treatments re
 viewed at regular time intervals. In healthcare settings\, individuals c
 an be observed and treated at irregular time intervals and this irregula
 rity may well be related to previous treatments and it can also influenc
 e future treatment. Not much is known about performance of MSMs in irreg
 ular data settings. On the basis of the foregoing\, this research sought
  to investigate application of MSMs to irregular data settings.  \n\nThe
  aim of this research was to investigate applicability and performance o
 f Marginal Structural Models to estimate causal effects in health data s
 ettings where individual patients may be observed at different (or “irre
 gular”) time intervals\, and these intervals themselves may be related t
 o treatment and confounder histories. A new class of Inverse Probability
  of Treatment Weighted (IPTW) estimators for irregular data was proposed
  to address the aim of the thesis. In this talk\, I present the proposed
  IPTW estimator for irregular data and results from a ‘blinded simulatio
 n study’ that demonstrate how the estimators can be used in a ‘real life
 ’ healthcare data setting.\n
STATUS:TENTATIVE
TRANSP:TRANSPARENT
CLASS:PUBLIC
LOCATION:Room G306A\, Jean McFarlane Building \, Oxford Rd\, Manchester\,
  M139PY
END:VEVENT
END:VCALENDAR