A1505
Title: Doubly robust pivotal pointwise confidence intervals for a monotonic continuous treatment effect curve
Authors: Charles Doss - University of Minnesota (United States) [presenting]
Abstract: A large majority of literature on evaluating the significance of a treatment effect based on observational data has been focused on discrete treatments. These methods are not applicable to drawing inferences for a continuous treatment, which arises in many important applications. Doubly robust confidence intervals are developed for the continuous treatment effect curve (at a fixed point) under the assumption that it is monotonic by developing a likelihood ratio-type procedure. Monotonicity is often a very natural assumption in the setting of a continuous treatment effect curve, and the assumption of monotonicity removes the need to choose a smoothing parameter for the nonparametrically estimated curve (or the related need to estimate the curve's unknown bias, which is challenging). The new methods are illustrated via simulations and a study of a dataset relating the effect of nurse staffing hours on hospital performance.
