Package: AIPW 0.6.9.3

AIPW: Augmented Inverse Probability Weighting

The 'AIPW' package implements the augmented inverse probability weighting, a doubly robust estimator, for average causal effect estimation with user-defined stacked machine learning algorithms. To cite the 'AIPW' package, please use: "Yongqi Zhong, Edward H. Kennedy, Lisa M. Bodnar, Ashley I. Naimi (2021). AIPW: An R Package for Augmented Inverse Probability Weighted Estimation of Average Causal Effects. American Journal of Epidemiology. <doi:10.1093/aje/kwab207>". Visit: <https://yqzhong7.github.io/AIPW/> for more information.

Authors:Yongqi Zhong [aut, cre], Ashley Naimi [aut], Gabriel Conzuelo [ctb], Edward Kennedy [ctb]

AIPW_0.6.9.3.tar.gz
AIPW_0.6.9.3.zip(r-4.7)AIPW_0.6.9.3.zip(r-4.6)AIPW_0.6.9.3.zip(r-4.5)
AIPW_0.6.9.3.tgz(r-4.6-any)AIPW_0.6.9.3.tgz(r-4.5-any)
AIPW_0.6.9.3.tar.gz(r-4.7-any)AIPW_0.6.9.3.tar.gz(r-4.6-any)
AIPW_0.6.9.3.tgz(r-4.6-emscripten)
manual.pdf |manual.html✨
DESCRIPTION |NEWS
card.svg |card.png
AIPW/json (API)

# Install 'AIPW' in R:
install.packages('AIPW', repos = c('https://yqzhong7.r-universe.dev', 'https://cloud.r-project.org'))

Bug tracker:https://github.com/yqzhong7/aipw/issues

Datasets:

On CRAN:

Conda:

causal-inferencemachine-learningrobust-estimators

7.72 score 28 stars 1 packages 63 scripts 983 downloads 11 mentions 6 exports 43 dependencies

Last updated from:23a85c46ea. Checks:9 OK. Indexed: yes.

TargetResultTimeFilesSyslog
linux-devel-x86_64OK210
source / vignettesOK275
linux-release-x86_64OK146
macos-release-arm64OK239
macos-oldrel-arm64OK191
windows-develOK263
windows-releaseOK107
windows-oldrelOK110
wasm-releaseOK118

Exports:AIPWAIPW_baseAIPW_nuisAIPW_tmleaipw_wrapperRepeated

Dependencies:bitopscaToolsclicodetoolscpp11cvAUCdata.tabledigestfarverforeachfuturefuture.applygamggplot2globalsgluegplotsgtablegtoolsisobanditeratorsKernSmoothlabelinglifecyclelistenvnnlsnumDerivparallellyprogressrR6RColorBrewerRcppRcppArmadillorlangROCRRsolnpS7scalesSuperLearnertruncnormvctrsviridisLitewithr

Getting Started with AIPW
Installation | Input data for analyses | Using AIPW to estimate the average treatment effect | One line version (Method chaining from R6class) | A more detailed tutorial | 1. Create an AIPW object | Use SuperLearner libraries | Use sl3 libraries | 2. Fit the AIPW object | 3. Calculate average treatment effects | Estimate the ATE with propensity scores truncation | Check the balance of propensity scores and inverse probability weights by exposure status after truncation | 4. Calculate average treatment effects among the treated/controls | stratified_fit() fits the outcome model by exposure status while fit() does not. Hence, stratified_fit() must be used to compute ATT/ATC (Kennedy et al. 2015) | Parallelization with future.apply | Use tmle/tmle3 fitted object as input | 1. tmle | 2. tmle3
Rendered fromAIPW.Rmdusingknitr::rmarkdown

Last update: 2025-04-05
Started: 2020-05-10

Repeated Cross-fitting
Create an AIPW object | Decorate with Repeated class | More num_reps vs More k-split? | References:
Rendered fromRepated_Crossfitting.Rmdusingknitr::rmarkdown

Last update: 2023-11-04
Started: 2023-11-04