SummarizeSpikeSlabCoefficients: Numerical summaries of coefficients from a spike and slab regression.

Description

Produces a summary of the marginal distribution of model coefficients from a spike and slab regression.

Usage

SummarizeSpikeSlabCoefficients(beta, burn = 0, order = TRUE)

Value

A five-column matrix with rows representing model coefficients. The first two columns are the posterior mean and standard deviation of each coefficient, including the point mass at zero. The next two columns are the posterior mean and standard deviations conditional on the coefficient being nonzero. The last column is the probability of a nonzero coefficient.

Arguments

beta: A matrix containing MCMC draws of regression coefficients. Each row is an MCMC draw. Each column is a coefficient.
burn: The number of MCMC iterations in the ojbect to be discarded as burn-in.
order: Logical. If TRUE then the coefficients are presented in order of their posterior inclusion probabilities. Otherwise the order of the coefficients is the same as in object.

Author

Steven L. Scott

Examples

Run this code

  n <- 100
  p <- 10
  ngood <- 3
  niter <- 1000
  sigma <- 2

  x <- cbind(1, matrix(rnorm(n * (p-1)), nrow=n))
  beta <- c(rnorm(ngood), rep(0, p - ngood))
  y <- rnorm(n, x %*% beta, sigma)
  x <- x[,-1]
  model <- lm.spike(y ~ x, niter=niter)
  plot(model)
  plot.ts(model$beta)
  hist(model$sigma)  ## should be near 8
  summary(model)
  SummarizeSpikeSlabCoefficients(model$beta, burn = 100)