https://github.com/cran/bbmle
Tip revision: 36784d90bc79081cfd43dc1b8bc4a82bf62d584f authored by Ben Bolker on 02 January 2012, 18:18:48 UTC
version 1.0.4
version 1.0.4
Tip revision: 36784d9
BIC-methods.Rd
\name{BIC-methods}
\docType{methods}
\alias{BIC}
\alias{BIC-methods}
\alias{AIC-methods}
\alias{AICc-methods}
\alias{logLik-methods}
\alias{AICc}
\alias{AIC,mle2-method}
\alias{AICc,mle2-method}
\alias{AICc,logLik-method}
\alias{AICc,ANY-method}
\alias{AICc,ANY,mle2,logLik-method}
\alias{qAICc}
\alias{qAICc-methods}
\alias{qAICc,ANY-method}
\alias{qAICc,mle2-method}
\alias{qAICc,logLik-method}
\alias{qAIC}
\alias{qAIC-methods}
\alias{qAIC,ANY-method}
\alias{qAIC,mle2-method}
\alias{qAIC,logLik-method}
\alias{BIC,logLik-method}
\alias{BIC,ANY-method}
\alias{BIC,mle2-method}
\alias{BIC,ANY,mle2,logLik-method}
\alias{qAIC,ANY,mle2,logLik-method}
\alias{qAICc,ANY,mle2,logLik-method}
\alias{logLik,mle2-method}
\alias{anova,mle2-method}
\title{Log likelihoods and model selection for mle2 objects}
\description{
Various functions for likelihood-based and information-theoretic
model selection of likelihood models
}
\section{Methods}{
\describe{
\item{logLik}{\code{signature(object = "mle2")}: Extract maximized
log-likelihood.}
\item{AIC}{\code{signature(object = "mle2")}: Calculate
Akaike Information Criterion}
\item{AICc}{\code{signature(object = "mle2")}: Calculate
small-sample corrected Akaike Information Criterion}
\item{BIC}{\code{signature(object = "mle2")}: Calculate
Bayesian (Schwarz) Information Criterion}
\item{BIC}{\code{signature(object = "logLik")}: Calculate
Bayesian (Schwarz) Information Criterion}
\item{BIC}{\code{signature(object = "ANY")}: Calculate
Bayesian (Schwarz) Information Criterion}
\item{anova}{\code{signature(object="mle2")}: Likelihood Ratio Test
comparision of different models}
}
}
\usage{
\S4method{BIC}{ANY,mle2,logLik}(object,...)
\S4method{AICc}{ANY,mle2,logLik}(object,...,nobs,k=2)
\S4method{qAIC}{ANY,mle2,logLik}(object,...,k=2)
\S4method{qAICc}{ANY,mle2,logLik}(object,...,nobs,k=2)
}
\arguments{
\item{object}{A \code{logLik} or \code{mle2} object}
\item{...}{An optional list of additional \code{logLik}
or \code{mle2} objects (fitted to the same data set).}
\item{nobs}{Number of observations (sometimes
obtainable as an attribute of
the fit or of the log-likelihood)}
\item{k}{penalty parameter (nearly always left at its default value of 2)}
}
\details{
Further arguments to \code{BIC} can be specified
in the \code{...} list: \code{delta} (logical)
specifies whether to include a column for delta-BIC
in the output.
}
\value{
A table of the BIC values, degrees of freedom,
and possibly delta-BIC values relative to the
minimum-BIC model
}
\note{This is implemented in an ugly way and could
probably be improved!}
\examples{
d <- data.frame(x=0:10,y=c(26, 17, 13, 12, 20, 5, 9, 8, 5, 4, 8))
(fit <- mle2(y~dpois(lambda=ymax/(1+x/xhalf)),
start=list(ymax=25,xhalf=3),data=d))
(fit2 <- mle2(y~dpois(lambda=(x+1)*slope),
start=list(slope=1),data=d))
BIC(fit,nobs=nrow(d))
BIC(fit,fit2,nobs=nrow(d))
}
\keyword{methods}