Bayesian Additive Regression Trees
Get Full Posterior Distribution
Get Number of Cores Used by BART
Predict for Test Data with Known Outcomes
Build a BART Model
Create an array of BART models for the same data.
Build BART-CV
Calculate Credible Intervals
Calculate Prediction Intervals
Check BART Error Assumptions
Importance Test for Covariate(s) of Interest
Destroy BART Model (deprecated --- do not use!)
Dummify Design Matrix
Gets Raw Node data
Gets Training Sample Projection / Weights
Get Posterior Error Variance Estimates
Get the Variable Inclusion Counts
Get the Variable Inclusion Proportions
Explore Pairwise Interactions in BART Model
Explore Variable Inclusion Proportions in BART Model
Estimate Out-of-sample Error with K-fold Cross validation
Test of Linearity
Gets node predictions indices of the training data for new data.
Partial Dependence Plot
Plot Convergence Diagnostics
Plot the fitted Versus Actual Response
Make a prediction on data using a BART object
Make a prediction on data using a BART array object
Summarizes information about a bartMachine
object.
Assess the Out-of-sample RMSE by Number of Trees
Set the Number of Cores for BART
Summarizes information about a bartMachine
object.
Perform Variable Selection using Three Threshold-based Procedures
Perform Variable Selection Using Cross-validation Procedure
An advanced implementation of Bayesian Additive Regression Trees with expanded features for data analysis and visualization.