Movatterモバイル変換


[0]ホーム

URL:


PSPI

R-CMD-checkversionRC++

The R packagePSPI (Propensity Score PredictiveInference) provides a suite of Propensity Score Predictive Inference(PSPI) methods to generalize treatment effects in trials to targetpopulations. The package includes an existing model Bayesian CausalForest (BCF) and four PSPI models (BCF-PS, FullBART, SplineBART,DSplineBART). These methods leverage Bayesian Additive Regression Trees(BART) to adjust for high-dimensional covariates and nonlinearassociations, while SplineBART and DSplineBART further use propensityscore based splines to address covariate shift between trial data andtarget population.

Installation

This package is based onRcpp,RcppArmadillo,RcppDist, andpg,please make sure these three packages can be installed.

This package can be installed from R CRAN:

install.packages("PSPI")library(PSPI)

or Github:

require("devtools")install_github("https://github.com/zjg540066169/PSPI")library(PSPI)

Attribution

This package includes code derived from theBART3package, originally developed by Rodney Sparapani.

The original source code, licensed under the GNU General PublicLicense version 2 (GPL-2), has been modified as follows: - We includepart of the C++ code in BART3, primarily about functions aboutwbart andcpwart. We also modify some files tomake sure our package can be successfully compiled. - Modifications weremade by Jungang Zou, 2024.

Licensing

Here are some acronyms:


[8]ページ先頭

©2009-2025 Movatter.jp