CMStatistics 2020: Start Registration
View Submission - CMStatistics
Title: Instrumental variable estimation of causal hazard ratio Authors:  Linbo Wang - University of Toronto (Canada) [presenting]
Eric Tchetgen Tchetgen - University of Pennsylvania (United States)
Torben Martinussen - University of Copenhagen (Denmark)
Stijn Vansteelandt - Ghent University and London School of Hygiene and Tropical Medicine (Belgium)
Abstract: Cox's proportional hazards model is one of the most popular statistical models to evaluate associations of a binary exposure with a censored failure time outcome. When confounding factors are not fully observed, the exposure hazard ratio estimated using a Cox model is not causally interpretable. To address this, we propose novel approaches for identification and estimation of the causal hazard ratio in the presence of unmeasured confounding factors. Our approaches are based on a binary instrumental variable and an additional no-interaction assumption. We derive, to the best of our knowledge, the first consistent estimator of the population marginal causal hazard ratio within an instrumental variable framework. Our estimator admits a closed-form representation. Hence it avoids the drawbacks of estimating equation based estimators. The approach is illustrated via simulation studies and data analysis.