UK Causal Inference Meeting 2015 Conference Programme : 15 th - 17 th April 2015

This is the third meeting in an initiative to organise a regular UK based meeting on causal inference as a collaborative effort across the methodology research community in the health and social sciences. The first meeting was held in Manchester in May 2013 and the second meeting was held in Cambridge in April 2014. UK-CIM aims to: provide a forum for people interested in causal inference to meet informally; for early career researchers to highlight their work; and to offer opportunities for networking to foster future research opportunities and collaborations. The theme of the meeting is " Causal Inference in Health, Economic and Social Sciences ". Causal inference is broadly defined, and the focus is on methodology and challenging applications, though presentations relating to interesting applications that highlight necessary methodological extensions are also encouraged SuSTaIN SuSTaIn is Statistics underpinning Science, Technology and Industry, a programme with the ambitious goal of strengthening the discipline of Statistics in the UK, by equipping it to face the challenges of future applications. Thus the focus is on rigorous and innovative new theory and methodology – core statistics for the 21st century – aimed at and stimulated by generic challenges raised by the 'data revolution', in areas as diverse as genomics, astronomy, telecommunications and finance. It is funded principally by a 3.5million Science and Innovation award from EPSRC, and partly by the University of Bristol, and runs from 2006 to 2016. At this year's UK-CIM, the MRC Integrative Epidemiology Unit at the University of Bristol (MRC IEU) funds one invited speaker, Prof Eric Tchetgen Tchtegen (Harvard). The MRC IEU conducts advanced population health science research to improve our understanding of the biological and environmental factors that can underlie and trigger common disease. Mendelian randomization with invalid instruments: bias from pleiotropy detected by simple graphical and statistical tests. Convex combination of ordinary least squares and two-stage least squares estimators. Unification of the instrumental variable approach for causal inference and missing data. Instrumental variable approaches for estimating causal effects in settings with multivariate outcomes. A structural Cox model for the causal effect of exposure among the exposed in an IV setting. Causal and statistical inference with social network data: Massive challenges and meager progress. Treatment effect of the treated: Understanding time-dependent confounding in survival analysis. A simple to implement algorithm for natural direct and indirect effects in survival studies with a repeatedly measured mediator. Mediation analysis of …