Abstract
We propose a class of stochastic intensity interventions for time-to-event settings, which operate by scaling the observed intensity governing an intermediate event. This gives rise to a family of estimands indexed by the scaling parameter, which changes the intermediate event rate while respecting natural heterogeneity. We further introduce calibrated interventions, where the scaling parameter is chosen to achieve a pre-specified goal, such as a desired level of cumulative risk of the intermediate event, and define corresponding composite target parameters capturing the resulting effects on an outcome process. We study the resulting estimation problem, presenting efficient influence curves for various versions of target and auxiliary parameters under a nonparametric statistical model, and derive and discuss double robustness properties. Our proposal relaxes positivity assumptions, and might offer a pragmatic analogue to indirect/direct effect decompositions. For estimation, we sketch a procedure based on targeted maximum likelihood estimation (TMLE). The proposed estimands are illustrated through simulated clinical scenarios addressing distinct causal questions.