sampleGlobalErrorVarianceOneIteration: Sample Global Error Variance

In stochtree: Stochastic Tree Ensembles (XBART and BART) for Supervised Learning and Causal Inference

Sample Global Error Variance

Description

Sample one iteration of the (inverse gamma) global variance model

This function is intended for advanced use cases in which users require detailed control of sampling algorithms and data structures. Minimal input validation and error checks are performed – users are responsible for providing the correct inputs. For tutorials on the "proper" usage of the stochtree's advanced workflow, we provide several vignettes at https://stochtree.ai/

Usage

sampleGlobalErrorVarianceOneIteration(residual, dataset, rng, a, b)

Arguments

residual	Outcome class
dataset	ForestDataset class
rng	C++ random number generator
a	Global variance shape parameter
b	Global variance scale parameter

Value

None

Examples

X <- matrix(runif(10*100), ncol = 10)
y <- -5 + 10*(X[,1] > 0.5) + rnorm(100)
y_std <- (y-mean(y))/sd(y)
forest_dataset <- createForestDataset(X)
outcome <- createOutcome(y_std)
rng <- createCppRNG(1234)
a <- 1.0
b <- 1.0
sigma2 <- sampleGlobalErrorVarianceOneIteration(outcome, forest_dataset, rng, a, b)

stochtree documentation built on April 29, 2026, 1:08 a.m.