HyperPara.Select

an "n" by "n" binary adjacent matrix (0/1) for the network configuration with n=length(pvalue)

a vector of p-values obtained from large scale statistical hypothesis testing

pvalue

a vector of possible choices for "pi0" in an increasing order

piall

a vector of possible choices of "rho0" and "rho1" in an increasing order

rhoall

a number of iterations you set for Bayesian Model Averaging. The default setting is 30, which is accord with the embedded inner process of in function <code>Networks.STD()</code> and <code>Networks.Fast()</code>. More iterations could be set if you have a desire to have more accurate parameter


This function is aiming at selecting appropriate hyper parameters by Bayesian Model Averaging. This process of this function has already embedded in function <code>Networks.STD()</code> and <code>Networks.Fast()</code>. The purpose of this function is for having the selected hyper-parameters independently. <p></p><p></p>

Provides a full package of posterior inference, model comparison, and graphical illustration of model fitting. A parallel computing algorithm for the Markov chain Monte Carlo (MCMC) based posterior inference and an Expectation-Maximization (EM) based algorithm for posterior approximation are are developed, both of which greatly reduce the computational time for model inference.

Zhou Lan

BANFF

Bayesian Network Feature Finder

HyperPara.Select function


This function is aiming at selecting appropriate hyper parameters by Bayesian Model Averaging. This process of this function has already embedded in function <code>Networks.STD()</code> and <code>Networks.Fast()</code>. The purpose of this function is for having the selected hyper-parameters independently. 



HyperPara.Select: Selecting Hyper Parameters by Bayesian Model Averaging

Description

Usage

Arguments

Value

References