predict_betas: Compute posterior predictive evaluates of covariate effect...

In VCBART: Fit Varying Coefficient Models with Bayesian Additive Regression Trees

Compute posterior predictive evaluates of covariate effect functions.

Description

Given an object returned by VCBART_ind or VCBART_cs and matrices of continuous and categorical modifiers, returns MCMC samples of the coefficient functions evaluated the provided points.

Usage

predict_betas(fit,
              Z_cont = matrix(0, nrow = 1, ncol = 1),
              Z_cat =  matrix(0, nrow = 1, ncol = 1),
              verbose = TRUE)

Arguments

fit	A list returned by VCBART_ind or VCBART_cs
Z_cont	Matrix of continuous modifiers at which you wish to evaluate the covariate effect functions. Default is a 1x1 matrix, which signals that no continuous modifiers are required for these evaluations.
Z_cat	Integer matrix of categorical modifiers at which you wish to evaluate the covariate effect functions. Default is a 1x1 matrix, which signals that no continuous modifiers are required for these evaluations.
verbose	Boolean indicating whether the code should print its progress (TRUE). Default is TRUE.

Value

An array of size nd x N x (p+1) where nd is the total number of MCMC draws, N is the total number of points at which you are evaluating the covariate effect functions (i.e. nrow(Z_cont) or nrow(Z_cat)), and p is the number of covariates. Note that the intercept function is included as the first slice in the third dimension.

VCBART documentation built on April 21, 2026, 9:07 a.m.