Doubly-Robust Nonparametric Estimation and Inference

Targeted minimum loss-based estimators of counterfactual means and causal effects that are doubly-robust with respect both to consistency and asymptotic normality (Benkeser et al (2017), ; MJ van der Laan (2014), ).


December 18, 2018

  • Version 1.0.4 released on GitHub and CRAN
  • Resolves issues arising from returnModels option when users input nuisance parameters
  • Add option to bypass future calls for easier debugging
  • Fixes to bugs in standard TMLE implementation -- namely, more robust fluctuations and corrected variance estimators

July 2, 2018

  • Version 1.0.3 released on GitHub and CRAN
  • Fix warnings on CRAN builds

February 5, 2018

  • Version 1.0.2 released on GitHub and CRAN
  • Replace foreach parallelization with future
  • More robust super learner methods included
  • Fix test to pass build with long doubles removed
  • Return estimated influence functions with drtmle fit for power users
  • Minor documentation corrections and updates

December 11, 2017

  • Version released on GitHub
  • More robust convex combination SuperLearner implemented.

August 17, 2017

  • Version 1.0.0 released on CRAN.
  • Version released on GitHub.

August 15, 2017:

  • Version 1.0.0 ready for CRAN release.

April 05, 2017:

  • The first public release of this package (v. 0.0.1) is made available on GitHub.

Reference manual

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


1.0.5 by David Benkeser, a year ago

Report a bug at

Browse source code at

Authors: David Benkeser [aut, cre, cph] , Nima Hejazi [ctb]

Documentation:   PDF Manual  

MIT + file LICENSE license

Imports SuperLearner, np, future, doFuture, future.apply, future.batchtools

Suggests testthat, knitr, rmarkdown, gam, earth, quadprog, nloptr, parallel, foreach, stringi

See at CRAN