preds_bbma_lin_alg {bartBMA}

R Documentation

Predictions for bart-bma output obtained from the posterior probability weighted averaged of the posterior means for each model

Description

This function produces predictions from BART-BMA by obtaining the posterior probability weighted averaged of the posterior means for each model.

Usage

preds_bbma_lin_alg(
  object,
  num_iter,
  burnin,
  newdata = NULL,
  update_resids = 1,
  trainingdata
)

Arguments

object	bartBMA object obtained from function bartBMA
num_iter	Total number of iterations of the Gibbs sampler (including burn-in).
burnin	Number of burn-on iterations of the Gibbs sampler.
newdata	Test data for which predictions are to be produced. Default = NULL. If NULL, then produces prediction intervals for training data if no test data was used in producing the bartBMA object, or produces prediction intervals for the original test data if test data was used in producing the bartBMA object.
update_resids	Option for whether to update the partial residuals in the gibbs sampler. If equal to 1, updates partial residuals, if equal to zero, does not update partial residuals. The defaullt setting is to update the partial residua;s.
trainingdata	The matrix of training data.

Value

A vector of predictions.

Examples

#set the seed
set.seed(100)
#simulate some data
N <- 100
p<- 100
epsilon <- rnorm(N)
xcov <- matrix(runif(N*p), nrow=N)
y <- sin(pi*xcov[,1]*xcov[,2]) + 20*(xcov[,3]-0.5)^2+10*xcov[,4]+5*xcov[,5]+epsilon
epsilontest <- rnorm(N)
xcovtest <- matrix(runif(N*p), nrow=N)
ytest <- sin(pi*xcovtest[,1]*xcovtest[,2]) + 20*(xcovtest[,3]-0.5)^2+10*xcovtest[,4]+
  5*xcovtest[,5]+epsilontest

#Train the object 
bart_bma_example <- bartBMA(x.train = xcov,y.train=y,x.test=xcovtest,zero_split = 1, 
                            only_max_num_trees = 1,split_rule_node = 0)
#Obtain the prediction intervals
preds_bbma_lin_alg(bart_bma_example,1000,100,newdata=xcovtest)

---