Generates credible intervals for \(\hat{f}(x)\) for a specified set of observations.
calc_credible_intervals(bart_machine, new_data,
ci_conf = 0.95)
An object of class ``bartMachine''.
A data frame containing observations at which credible intervals for \(\hat{f}(x)\) are to be computed.
Confidence level for the credible intervals. The default is 95%.
Returns a matrix of the lower and upper bounds of the credible intervals for each observation in new_data
.
This interval is the appropriate quantiles based on the confidence level, ci_conf
, of the predictions
for each of the Gibbs samples post-burn in.
# NOT RUN { #generate Friedman data set.seed(11) n = 200 p = 5 X = data.frame(matrix(runif(n * p), ncol = p)) y = 10 * sin(pi* X[ ,1] * X[,2]) +20 * (X[,3] -.5)^2 + 10 * X[ ,4] + 5 * X[,5] + rnorm(n) ##build BART regression model bart_machine = bartMachine(X, y) #get credible interval cred_int = calc_credible_intervals(bart_machine, X) print(head(cred_int)) # }