rnodeDAGWishart {BCDAG}R Documentation

Draw one observation from a Normal-Inverse-Gamma distribution (internal function)

Description

This function performs one draw from the Multivariate-Normal-Inverse-Gamma (prior/posterior) distribution of the parameters of a Normal linear regression model. Response variable is node and covariates are given by the parents of node in DAG. It is implemented node-by-node in rDAGWishart to obtain draws from a compatible (prior/posterior) DAG-Wishart distribution.

Usage

rnodeDAGWishart(node, DAG, aj, U)

Arguments

node

numerical label of the node in DAG

DAG

(q,q) adjacency matrix of the DAG

aj

common shape hyperparameter of the compatible DAG-Wishart, a > q - 1

U

position hyperparameter of the compatible DAG-Wishart, a (q, q) s.p.d. matrix

Value

A list with two elements; a vector with one draw for the (vector) regression coefficient and a scalar with one draw for the conditional variance


[Package BCDAG version 1.0.0 Index]