Package: CBPS 0.23

CBPS: Covariate Balancing Propensity Score

Implements the covariate balancing propensity score (CBPS) proposed by Imai and Ratkovic (2014) <doi:10.1111/rssb.12027>. The propensity score is estimated such that it maximizes the resulting covariate balance as well as the prediction of treatment assignment. The method, therefore, avoids an iteration between model fitting and balance checking. The package also implements optimal CBPS from Fan et al. (in-press) <doi:10.1080/07350015.2021.2002159>, several extensions of the CBPS beyond the cross-sectional, binary treatment setting. They include the CBPS for longitudinal settings so that it can be used in conjunction with marginal structural models from Imai and Ratkovic (2015) <doi:10.1080/01621459.2014.956872>, treatments with three- and four-valued treatment variables, continuous-valued treatments from Fong, Hazlett, and Imai (2018) <doi:10.1214/17-AOAS1101>, propensity score estimation with a large number of covariates from Ning, Peng, and Imai (2020) <doi:10.1093/biomet/asaa020>, and the situation with multiple distinct binary treatments administered simultaneously. In the future it will be extended to other settings including the generalization of experimental and instrumental variable estimates.

Authors:Christian Fong [aut, cre], Marc Ratkovic [aut], Kosuke Imai [aut], Chad Hazlett [ctb], Xiaolin Yang [ctb], Sida Peng [ctb], Inbeom Lee [ctb]

CBPS_0.23.tar.gz
CBPS_0.23.zip(r-4.5)CBPS_0.23.zip(r-4.4)CBPS_0.23.zip(r-4.3)
CBPS_0.23.tgz(r-4.4-any)CBPS_0.23.tgz(r-4.3-any)
CBPS_0.23.tar.gz(r-4.5-noble)CBPS_0.23.tar.gz(r-4.4-noble)
CBPS_0.23.tgz(r-4.4-emscripten)CBPS_0.23.tgz(r-4.3-emscripten)
CBPS.pdf |CBPS.html
CBPS/json (API)

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

Peer review:

Datasets:
  • Blackwell - Blackwell Data for Covariate Balancing Propensity Score
  • LaLonde - LaLonde Data for Covariate Balancing Propensity Score

On CRAN:

This package does not link to any Github/Gitlab/R-forge repository. No issue tracker or development information is available.

4.52 score 6 packages 160 scripts 2.3k downloads 5 mentions 9 exports 21 dependencies

Last updated 3 years agofrom:1d5dae9a31. Checks:OK: 7. Indexed: yes.

TargetResultDate
Doc / VignettesOKNov 03 2024
R-4.5-winOKNov 03 2024
R-4.5-linuxOKNov 03 2024
R-4.4-winOKNov 03 2024
R-4.4-macOKNov 03 2024
R-4.3-winOKNov 03 2024
R-4.3-macOKNov 03 2024

Exports:AsyVarbalanceCBIVCBMSMCBPSCBPS.fithdCBPSnpCBPSvcov_outcome

Dependencies:backportschkclicodetoolsforeachglmnetglueiteratorslatticelifecycleMASSMatchItMatrixnnetnumDerivRcppRcppEigenRcppProgressrlangshapesurvival

Readme and manuals

Help Manual

Help pageTopics
Asymptotic Variance and Confidence Interval Estimation of the ATEAsyVar
Optimal Covariate Balancebalance
Calculates the pre- and post-weighting difference in standardized means for covariate within each contrastbalance.CBPS
Calculates the pre- and post-weighting correlations between each covariate and the Tbalance.CBPSContinuous
Calls the appropriate balance function based on the number of treatmentsbalance.npCBPS
Blackwell Data for Covariate Balancing Propensity ScoreBlackwell
Covariate Balancing Propensity Score for Instrumental Variable Estimates (CBIV)CBIV
Covariate Balancing Propensity Score (CBPS) for Marginal Structural ModelsCBMSM
CBMSM.fitCBMSM.fit
Covariate Balancing Propensity Score (CBPS) EstimationCBPS
CBPS.fit determines the proper routine (what kind of treatment) and calls the approporiate function. It also pre- and post-processes the dataCBPS.fit
hdCBPS high dimensional CBPS method to parses the formula object and passes the result to hdCBPS.fit, which calculates ATE using CBPS method in a high dimensional setting.hdCBPS hdCBPS.fit
LaLonde Data for Covariate Balancing Propensity ScoreLaLonde
Non-Parametric Covariate Balancing Propensity Score (npCBPS) EstimationnpCBPS
npCBPS.fitnpCBPS.fit
Plotting CBPS Estimation for Marginal Structural Modelsplot.CBMSM
Plotting Covariate Balancing Propensity Score Estimationplot.CBPS
Plot the pre-and-post weighting correlations between X and Tplot.CBPSContinuous
Calls the appropriate plot function, based on the number of treatmentsplot.npCBPS
Print coefficients and model fit statisticsprint.CBPS
Summarizing Covariate Balancing Propensity Score Estimationsummary.CBPS
Calculate Variance-Covariance Matrix for Outcome Modelvcov_outcome
vcov_outcomevcov_outcome.CBPSContinuous
Calculate Variance-Covariance Matrix for a Fitted CBPS Objectvcov.CBPS