bayess (version 1.4)

BayesReg: Bayesian linear regression output

Description

This function contains the R code for the implementation of Zellner's $G$-prior analysis of the regression model as described in Chapter 3. The purpose of BayesRef is dual: first, this R function shows how easily automated this approach can be. Second, it also illustrates how it is possible to get exactly the same type of output as the standard R function summary(lm(y~X)). In particular, it calculates the Bayes factors for variable selection, more precisely single variable exclusion.

Usage

BayesReg(y, X, g = length(y), betatilde = rep(0, dim(X)[2]), prt = TRUE)

Arguments

y

response variable

X

matrix of regressors

g

constant g for the $G$-prior

betatilde

prior mean on $\beta$

prt

boolean variable for printing out the standard output

Value

• postmeancoeff
  posterior mean of the regression coefficients
• postsqrtcoeff
  posterior standard deviation of the regression coefficients
• log10bf
  log-Bayes factors against the full model
• postmeansigma2
  posterior mean of the variance of the model
• postvarsigma2
  posterior variance of the variance of the model

Examples

data(faithful)
BayesReg(faithful[,1],faithful[,2])