BIC-methods {bbmle} | R Documentation |
Various functions for likelihood-based and information-theoretic model selection of likelihood models
## S4 method for signature 'ANY, mle2, logLik': BIC(object,...) ## S4 method for signature 'ANY, mle2, logLik': qAIC(object,...) ## S4 method for signature 'ANY, mle2, logLik': qAICc(object,...)
object |
A logLik or mle2 object |
... |
An optional list of additional logLik
or mle2 objects (fitted to the same data set).
If the number of attributes has not been included as an attribute of
the fit or of the log-likelihood, it can specified as
nobs= in this list. |
Further arguments to BIC
can be specified
in the ...
list: delta
(logical)
specifies whether to include a column for delta-BIC
in the output.
A table of the BIC values, degrees of freedom, and possibly delta-BIC values relative to the minimum-BIC model
signature(object = "mle2")
: Extract maximized
log-likelihood.signature(object = "mle2")
: Calculate
Akaike Information Criterionsignature(object = "mle2")
: Calculate
small-sample corrected Akaike Information Criterionsignature(object = "mle2")
: Calculate
Bayesian (Schwarz) Information Criterionsignature(object = "logLik")
: Calculate
Bayesian (Schwarz) Information Criterionsignature(object = "ANY")
: Calculate
Bayesian (Schwarz) Information Criterionsignature(object="mle2")
: Likelihood Ratio Test
comparision of different modelsThis is implemented in an ugly way and could probably be improved!
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))) (fit2 <- mle2(y~dpois(lambda=(x+1)*slope), start=list(slope=1))) BIC(fit,nobs=length(x)) BIC(fit,fit2,nobs=length(x))