bbricks (version 0.1.1)

rPosteriorPredictive.GaussianNIG: Posterior predictive random generation of a "GaussianNIG" object

Description

Generate random samples from the posterior predictive distribution of the following structure: beta,sigma^2|gamma ~ NIG(gamma) x|beta,sigma^2,X ~ Gaussian(X where gamma = (m,V,a,b) is the Normal-Inverse-Gamma(NIG) parameter, "m" is a numeric "location" parameter; "V" is a symmetric positive definite matrix representing the "scale" parameters; "a" and "b" are the "shape" and "rate" parameter of the Inverse Gamma distribution. The model structure and prior parameters are stored in a "GaussianNIG" object. Posterior predictive is a distribution of x|gamma,X.

Usage

# S3 method for GaussianNIG
rPosteriorPredictive(obj, n, X, ...)

Arguments

obj

A "GaussianNIG" object.

n

integer, number of samples.

X

matrix, the location of the prediction, each row is a location.

...

Additional arguments to be passed to other inherited types.

Value

A matrix of n rows and nrow(X) columns, each row is a sample.

References

Banerjee, Sudipto. "Bayesian Linear Model: Gory Details." Dowloaded from http://www. biostat. umn. edu/~ ph7440 (2008).

See Also

@seealso GaussianNIG, dPosteriorPredictive.GaussianNIG

Examples

# NOT RUN {
obj <- GaussianNIG(gamma=list(m=c(1,1),V=diag(2),a=1,b=1))
X <- matrix(runif(20),ncol=2)
rPosteriorPredictive(obj=obj,n=3,X=X)
# }