Efficient Estimation of the Causal Effects of Stochastic Interventions

Efficient estimation of the population-level causal effects of stochastic interventions on a continuous-valued exposure. Both one-step and targeted minimum loss estimators are implemented for a causal parameter defined as the counterfactual mean of an outcome of interest under a stochastic intervention that may depend on the natural value of the exposure (i.e., a modified treatment policy). To accommodate settings in which two-phase sampling is employed, procedures for making use of inverse probability of censoring weights are provided to facilitate construction of inefficient and efficient one-step and targeted minimum loss estimators. The causal parameter and its estimation were first described by Díaz and van der Laan (2013) , while the multiply robust estimation procedure and its application to data arising in two-phase sampling designs was detailed in NS Hejazi, MJ van der Laan, HE Janes, PB Gilbert, and DC Benkeser (2020) . Estimation of nuisance parameters may be enhanced through the Super Learner ensemble model in 'sl3', available for download from GitHub using 'remotes::install_github("tlverse/sl3")'.


Reference manual

It appears you don't have a PDF plugin for this browser. You can click here to download the reference manual.


0.3.5 by Nima Hejazi, 6 months ago


Report a bug at https://github.com/nhejazi/txshift/issues

Browse source code at https://github.com/cran/txshift

Authors: Nima Hejazi [aut, cre, cph] , David Benkeser [aut] , Iván Díaz [ctb] , Jeremy Coyle [ctb] , Mark van der Laan [ctb, ths]

Documentation:   PDF Manual  

MIT + file LICENSE license

Imports stats, stringr, data.table, assertthat, mvtnorm, hal9001, haldensify, lspline, ggplot2, tibble, scales, latex2exp, Rdpack, cli

Suggests testthat, knitr, rmarkdown, covr, future, future.apply, origami, ranger, Rsolnp, nnls, rlang

Enhances sl3

See at CRAN