All Times EDT
Keywords: causal inference, external control, TMLE
Real-world data (RWD) is playing an increasingly important role in drug development. In many scenarios, a concurrent control arm may not be viable for ethical or practical considerations, and inclusion of an external control arm can greatly facilitate the decision-making and interpretation of findings. To address the inherent confounding due to lack of randomization, propensity score matching method has been widely employed. Within the framework of causal inference, however, many alternatives have been proposed with desirable theoretical properties. In this talk, we review key steps from study design conceptualization to data source selection, and focus on several methods for evaluation of performance in the context of creating external control for clinical trials. We conducted a focused simulation studies to assess bias reduction and statistical properties when underlying assumptions are violated or models are mis-specified. The results support that analysis using matched group improve bias reduction when sample size is not a limiting factor, and targeted maximum likelihood estimation coupled with super learner is robust when estimating both average treatment effects and average treatment effects among treated.