Estimating marginal treatment effects from observational studies and indirect treatment comparisons: When are standardization-based methods preferable to those based on propensity score weighting?

TL;DR

This paper compares standardization-based methods and propensity score weighting for estimating treatment effects in observational studies and indirect treatment comparisons, highlighting when each approach is preferable based on simulation results.

Contribution

It introduces a comparative evaluation of standardization and propensity score methods in different settings, including a novel perspective on their analogy in indirect treatment comparisons.

Findings

Standardization methods often outperform propensity score weighting in certain scenarios.

Adjusting for purely prognostic factors is crucial for accurate treatment effect estimates.

Recommendations for conducting indirect treatment comparisons can be improved based on these findings.

Abstract

In light of newly developed standardization methods, we evaluate, via simulation study, how propensity score weighting and standardization -based approaches compare for obtaining estimates of the marginal odds ratio and the marginal hazard ratio. Specifically, we consider how the two approaches compare in two different scenarios: (1) in a single observational study, and (2) in an anchored indirect treatment comparison (ITC) of randomized controlled trials. We present the material in such a way so that the matching-adjusted indirect comparison (MAIC) and the (novel) simulated treatment comparison (STC) methods in the ITC setting may be viewed as analogous to the propensity score weighting and standardization methods in the single observational study setting. Our results suggest that current recommendations for conducting ITCs can be improved and underscore the importance of adjusting for purely prognostic factors.