Marginal structural models and causal inference in epidemiology

In observational studies with exposures or treatments that vary over time, standard approaches for adjustment of confounding are biased when there exi st time-dependent con founders that are also affected by previous treatment . This paper introduces marginal structural models, a new class of causal m odels that allow for improved adjustment of confounding in those situations . The parameters of a marginal structural model can be consistently estimat ed using a new class of estimators, the inverse-probability-of-treatment we ighted estimators.