Learn R Programming

cjbart

Overview

cjbart is an R package for analyzing conjoint experiments using Bayesian Additive Regression Trees (BART), specifically focusing on inspecting heterogeneous treatment effects.

This package is in its early stages of development, and core functionality is liable to change.

Installation

The latest development version of cjbart can be installed directly from this repository, using the following code:

# install.packages("devtools")
devtools::install_github("tsrobinson/cjbart")

Getting help

If you come across any issues, or have any suggestions for improvements, please raise an issue here.

Copy Link

Version

Install

install.packages('cjbart')

Monthly Downloads

257

Version

0.3.2

License

Apache License (>= 2.0)

Issues

Pull Requests

Stars

Forks

Maintainer

Thomas Robinson

Last Published

September 6th, 2023

Functions in cjbart (0.3.2)

plot.cjbart

Plot Marginal Component Effects of a cjbart Object
AMCE

Average Marginal Component Effect Estimation with Credible Interval
IMCE

Heterogeneous Effects Analysis of Conjoint Results
het_vimp

Estimate Variable Importance Metrics for cjbart Object
rf_vimp

Estimate a Single Variable Importance Metric for cjbart Object
cjbart

Generate Conjoint Model Using BART
plot.cjbart.vimp

Plot Variable Importance Matrix for Heterogeneity Analysis
RMCE

Inspect Round-Level Marginal Component Effect (RMCE)
pIMCE

Population-Weighted Heterogeneous Effects Analysis of Conjoint Results
summary.cjbart

Summarizing cjbart Marginal Component Effect Estimates