\name{MuMIn-package}
\alias{MuMIn-package}
\alias{MuMIn}
\docType{package}
\encoding{utf-8}
\title{Multi-model inference}
\description{
The package \pkg{MuMIn} contains functions to streamline information-theoretic
model selection and carry out model averaging based on the information criteria.
}
\details{
The collection of functions includes:
\describe{
\item{\code{\link{dredge}}}{performs automated model selection with
subsets of the supplied \sQuote{global} model, and optional
choices of other model properties (such as different link functions).
The set of models may be generated either with \sQuote{all possible}
combinations, or tailored according to the conditions specified.
\code{\link{pdredge}} does the same, but can parallelize model fitting
process using a cluster.
}
\item{\code{\link{model.sel}}}{creates a model selection table from
hand-picked models. }
\item{\code{\link{model.avg}}}{ calculates model averaged parameters,
with standard errors and confidence intervals. }
\item{\code{\link{AICc}}}{calculates second-order Akaike information
criterion. }
}
For a complete list of functions, use \code{library(help = "MuMIn")}.
By default, AIC\eqn{_{c}}{c} is used to rank the models and to obtain model
selection probabilities, though any other information criteria can be
utilised. At least the following ones are currently implemented in \R:
\code{\link{AIC}} and \code{\link{BIC}} in package \pkg{stats}, and
\code{\link{QAIC}}, \code{\link{QAICc}}, \code{\link{ICOMP}},
\code{\link{CAICF}}, and \link{Mallows' Cp} in \pkg{MuMIn}. There is also
\code{\link{DIC}} extractor for \acronym{MCMC} models, and \code{\link{QIC}} for
\acronym{GEE}.
Most of \R's common modelling functions are supported, for a full inventory
see \link[=MuMIn-models]{list of supported models}.
}
\author{ Kamil Barto\enc{ń}{n} }
\references{
Burnham, K. P. and Anderson, D. R (2002) \emph{Model selection and multimodel
inference: a practical information-theoretic approach}. 2nd ed. New York,
Springer-Verlag.
}
\seealso{
\code{\link{AIC}}, \code{\link{step}} or \code{\link[MASS]{stepAIC}} for stepwise
model selection by AIC.
}
\examples{
data(Cement)
fm1 <- lm(y ~ ., data = Cement)
ms1 <- dredge(fm1)
plot(ms1)
model.avg(ms1, subset = delta < 4)
confset.95p <- get.models(ms1, cumsum(weight) <= .95)
avgmod.95p <- model.avg(confset.95p)
summary(avgmod.95p)
confint(avgmod.95p)
}
\keyword{package}
\keyword{models}