Estimating marginal treatment effects from single studies and indirect treatment comparisons: When are standardization-based methods preferable to inverse probability of treatment weighting?

In light of newly developed standardization methods, we evaluate, via simulation study, how inverse probability of treatment weighting (IPTW) and standardization-based approaches compare for obtaining estimates of the marginal odds-ratio and the marginal hazards ratio. Specifically, we consider how the two approaches compare in two different scenarios: (1) in a single comparative study (either randomized or non-randomized), and (2) in an anchored indirect treatment comparison of randomized controlled trials (where we compare the matching-adjusted indirect comparison (MAIC) and simulated treatment comparison (STC) methods). We conclude that, in general, standardization-based methods with correctly specified outcome models are more efficient than those based on IPTW. While IPTW is robust to model misspecification in a single comparative study, we find that this is not necessarily the case for MAIC in an indirect treatment comparison.