Non-collapsible marginal effect measures depend on joint distributions of effect modifiers and prognostic variables, so unadjusted anchored indirect comparisons can be biased even without individual-level treatment effect heterogeneity.
Causal inference for meta-analysis and multi-level data structures, with application to randomized studies of Vioxx.Psychometrika2017; 82(2): 459–474
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
representative citing papers
citing papers explorer
-
Transportability of model-based estimands in evidence synthesis
Non-collapsible marginal effect measures depend on joint distributions of effect modifiers and prognostic variables, so unadjusted anchored indirect comparisons can be biased even without individual-level treatment effect heterogeneity.
- Incorporating estimands into meta-analyses of clinical trials