Two basic statistical strategies of conducting causal inference in real-world studies

Randomized controlled clinical trials are the gold standard in drug development, but their costs, duration, and limited generalizability have motivated some to look for real-world studies as alternatives. On the other hand, real-world studies may be less convincing due to the presence of confounding bias. In the literature of causal inference, a variety of statistical methods have been proposed to adjust for confounding bias. However, it is challenging for the users to understand the statistical properties enjoyed by each method and then explicitly specify its underlying model assumptions. As a tutorial, in this article, we investigate two basic statistical strategies of conducting causal inference in real-world studies, which cover many commonly used methods. These two strategies are the weighting strategy and the standardization strategy. The weighting strategy defines a target estimand using a propensity-score model (treatment assignment ~ confounders), while the standardization strategy defines an estimand using an outcome-regression model (outcome variable ~ treatment assignment + confounders). Although these two strategies are different at the beginning, at the end both of them are robust for estimating the treatment effect under the same set of identifiability conditions and therefore same kind of sensitivity analysis is needed for evaluating the impact caused by the violation of these conditions.