mcmcregress.rd

使用R语言的马尔科夫链蒙特卡洛模拟（MCMC）源代码程序。

\name{MCMCregress}
\alias{MCMCregress}
\title{Markov Chain Monte Carlo for Gaussian Linear Regression}
\description{
  This function generates a sample from the posterior distribution
  of a linear regression model with Gaussian errors using
  Gibbs sampling (with a multivariate Gaussian prior on the
  beta vector, and an inverse Gamma prior on the conditional
  error variance).  The user supplies data and priors, and 
  a sample from the posterior distribution is returned as an mcmc
  object, which can be subsequently analyzed with functions 
  provided in the coda package.
  }
  
\usage{
MCMCregress(formula, data = parent.frame(), burnin = 1000, mcmc = 10000,
   thin = 1, verbose = 0, seed = NA, beta.start = NA, 
   b0 = 0, B0 = 0, c0 = 0.001, d0 = 0.001,
   marginal.likelihood = c("none", "Laplace", "Chib95"), ...) }

\arguments{
    \item{formula}{Model formula.}

    \item{data}{Data frame.}

    \item{burnin}{The number of burn-in iterations for the sampler.}

    \item{mcmc}{The number of MCMC iterations after burnin.}

    \item{thin}{The thinning interval used in the simulation.  The number of
      MCMC iterations must be divisible by this value.}

    \item{verbose}{A switch which determines whether or not the progress of
    the sampler is printed to the screen.  If \code{verbose} is greater
    than 0 the iteration number, the
    \eqn{\beta}{beta} vector, and the error variance are printed to 
    the screen every \code{verbose}th iteration.}

    \item{seed}{The seed for the random number generator.  If NA, the Mersenne
    Twister generator is used with default seed 12345; if an integer is 
    passed it is used to seed the Mersenne twister.  The user can also
    pass a list of length two to use the L'Ecuyer random number generator,
    which is suitable for parallel computation.  The first element of the
    list is the L'Ecuyer seed, which is a vector of length six or NA (if NA 
    a default seed of \code{rep(12345,6)} is used).  The second element of 
    list is a positive substream number. See the MCMCpack 
    specification for more details.}

    \item{beta.start}{The starting values for the \eqn{\beta}{beta} vector.
    This can either be a scalar or a
    column vector with dimension equal to the number of betas.
    The default value of of NA will use the OLS
    estimate of \eqn{\beta}{beta} as the starting value.  If this is a 
    scalar,  that value will serve as the starting value
    mean for all of the betas.}

    \item{b0}{The prior mean of \eqn{\beta}{beta}.  This can either be a 
    scalar or a
    column vector with dimension equal to the number of betas. If this
    takes a scalar  value, then that value will serve as the prior
    mean for all of the betas.} 
    
    \item{B0}{The prior precision of \eqn{\beta}{beta}.  This can either be a 
    scalar or a square matrix with dimensions equal to the number of betas.  
    If this
    takes a scalar value, then that value times an identity matrix serves
    as the prior precision of beta. Default value of 0 is equivalent to
    an improper uniform prior for beta.}
    
  \item{c0}{\eqn{c_0/2}{c0/2} is the shape parameter for the inverse
    Gamma prior on \eqn{\sigma^2}{sigma^2} (the variance of the
    disturbances). The amount of information in the inverse Gamma prior
    is something like that from \eqn{c_0}{c0} pseudo-observations.} 
    
    \item{d0}{\eqn{d_0/2}{d0/2} is the scale parameter for the
    inverse Gamma prior on \eqn{\sigma^2}{sigma^2} (the variance of the
    disturbances). In constructing the inverse Gamma prior,
    \eqn{d_0}{d0} acts like the sum of squared errors from the
    \eqn{c_0}{c0} pseudo-observations.}

  \item{marginal.likelihood}{How should the marginal likelihood be
    calculated? Options are: \code{none} in which case the marginal
    likelihood will not be calculated, \code{Laplace} in which case the
    Laplace approximation (see Kass and Raftery, 1995) is used, and
    \code{Chib95} in which case the method of Chib (1995) is used.}
  
    \item{...}{further arguments to be passed}       
}

\value{
   An mcmc object that contains the posterior sample.  This 
   object can be summarized by functions provided by the coda package.
}

\details{
  \code{MCMCregress} simulates from the posterior distribution using 
  standard Gibbs sampling (a multivariate Normal draw for the betas, and an
  inverse Gamma draw for the conditional error variance).  The simulation
  proper is done in compiled C++ code to maximize efficiency.  Please consult
  the coda documentation for a comprehensive list of functions that can be
  used to analyze the posterior sample.
  
  The model takes the following form:
  \deqn{y_i = x_i ' \beta + \varepsilon_{i}}{y_i = x_i'beta + epsilon_i}
  Where the errors are assumed to be Gaussian:
  \deqn{\varepsilon_{i} \sim \mathcal{N}(0, \sigma^2)}{epsilon_i ~ N(0,
    sigma^2)} 
  We assume standard, semi-conjugate priors:
  \deqn{\beta \sim \mathcal{N}(b_0,B_0^{-1})}{beta ~ N(b0,B0^(-1))}
  And:
  \deqn{\sigma^{-2} \sim \mathcal{G}amma(c_0/2, d_0/2)}{sigma^(-2) ~
    Gamma(c0/2, d0/2)}
  Where \eqn{\beta}{beta} and \eqn{\sigma^{-2}}{sigma^(-2)} are assumed 
  \emph{a priori} independent.  Note that only starting values for
  \eqn{\beta}{beta} are allowed because simulation is done using
  Gibbs sampling with the conditional error variance
  as the first block in the sampler.
  }
  
  \references{
   Siddhartha Chib. 1995. "Marginal Likelihood from the Gibbs Output."
   \emph{Journal of the American Statistical Association}. 90:
   1313-1321.

   Robert E. Kass and Adrian E. Raftery. 1995. "Bayes Factors."
   \emph{Journal of the American Statistical Association}. 90: 773-795.
    
   Daniel Pemstein, Kevin M. Quinn, and Andrew D. Martin.  2007.  
   \emph{Scythe Statistical Library 1.0.} \url{http://scythe.wustl.edu}.
   
   Martyn Plummer, Nicky Best, Kate Cowles, and Karen Vines. 2002.
   \emph{Output Analysis and Diagnostics for MCMC (CODA)}.
   \url{http://www-fis.iarc.fr/coda/}.
}


\examples{
\dontrun{
line   <- list(X = c(-2,-1,0,1,2), Y = c(1,3,3,3,5))
posterior  <- MCMCregress(Y~X, data=line, verbose=1000)
plot(posterior)
raftery.diag(posterior)
summary(posterior)
}
}

\keyword{models}

\seealso{\code{\link[coda]{plot.mcmc}},
  \code{\link[coda]{summary.mcmc}}, \code{\link[stats]{lm}}}