BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:The concept of separable effects for causal mediation and competin
 g risks analyses - Vanessa Didelez\, Leibniz Institute for Prevention Rese
 arch and Epidemiology - BIPS\, Bremen\, Germany
DTSTART:20200221T140000Z
DTEND:20200221T150000Z
UID:TALK135964@talks.cam.ac.uk
CONTACT:Dr Sergio Bacallado
DESCRIPTION:In causal mediation analysis\, we are interested in understand
 ing different mechanisms (causal pathways) of a treatment or exposure affe
 cting some outcomes. Often this is formalised in terms of (in)direct causa
 l effects - popular notions of these are based on so-called “nested coun
 terfactuals”. These concepts however run into difficulties of interpreta
 tion in the particular context of survival analyses.  \n\nI will discuss t
 he problem and propose an alternative approach that does not suffer from s
 uch shortcomings [1]: this novel approach follows Robins and Richardson [2
 ]\, where mechanisms need to be specified allowing a separation into the d
 ifferent treatment paths\, formalized using an augmented directed acyclic 
 graph (DAG). It can be shown that under specific assumptions regarding the
  separability\, identification of such alternative mediated effects is pos
 sible\, resulting in the familiar mediation formula. In continuous time\, 
 it can further be shown that for the particular case of combining a linear
  model for the mediator with an additive hazard model\, the familiar “pa
 th-tracing” formula can be recovered [3].\n\nFor illustration\, this is 
 applied to an example of mediated effects of a blood-pressure treatment on
  time to kidney failure [3]. We investigate intensive versus standard bloo
 d-pressure treatment and find that there is little\, and not much time-var
 ying\, indirect effect via diastolic blood pressure on kidney failure. Hen
 ce\, other ways of preventing this side effect of intensive blood-pressure
  treatment might be worth investigated.\n\nThe proposed new approach solve
 s a crucial conceptual problem of mediation analysis with a survival outco
 me and can be extended to competing risks [4]. It is founded in decision t
 heory\, avoids genuine counterfactual assumptions and constitutes an inter
 esting alternative to the popular structural equation models.\n\nReference
 s\n\n[1] Didelez. Defining causal mediation with a longitudinal mediator a
 nd a survival outcome. Lifetime Data Analysis\, DOI: 10.1007/s10985-018-94
 49-0\, 2018.\n\n[2] Robins\, Richardson. Alternative graphical causal mode
 ls and the identification of direct effects. In: Causality and psychopatho
 logy: Finding the determinants of disorders and their cures\, pages 103-15
 8\, 2011.\n\n[3] Aalen\, Stensrud\, Didelez\, Daniel\, Roysland\, Strohmai
 er. Time-dependent mediators in survival analysis: Modelling direct and in
 direct effects with the additive hazards model. Biometrical Journal. 2019\
 ; (Epub 2019 Feb 19).\n\n[4] Stensrud\, Young\, Didelez\, Robins\, Hernán
 . Separable effects for causal inference in the presence of competing risk
 s. To appear in JASA.
LOCATION:MR12
END:VEVENT
END:VCALENDAR