| extractAIC {base} | R Documentation |
Extract AIC from a Fitted Model
Description
Computes the (generalized) Akaike Information Criterion for a fitted parametric model.
Usage
extractAIC (fit, scale, k = 2, ...)
extractAIC.lm (fit, scale = 0, k = 2, ...)
extractAIC.glm(fit, scale = 0, k = 2, ...)
extractAIC.aov(fit, scale = 0, k = 2, ...)
extractAIC.coxph (fit, scale, k = 2, ...)
extractAIC.negbin (fit, scale, k = 2, ...)
extractAIC.survreg(fit, scale, k = 2, ...)
Arguments
fit |
fitted model, usually the result of a fitter like
|
scale |
optional numeric specifying the scale parameter of the
model, see |
k |
numeric specifying the “weight” of the
equivalent degrees of freedom ( |
... |
further arguments (currently unused in base R). |
Details
The criterion used is
AIC = - 2\log L + k \times \mbox{edf},
where L is the likelihood
and edf the equivalent degrees of freedom (i.e., the number of
parameters for usual parametric models) of fit.
For generalized linear models (i.e., for lm,
aov, and glm), -2\log L is
the deviance, as computed by deviance(fit), plus
a constant.
k = 2 corresponds to the traditional AIC, using k =
log(n) provides the BIC (Bayes IC) instead.
For further information, particularly about scale, see
step.
Value
A numeric vector of length 2, giving
edf |
the “equivalent degrees of freedom”
of the fitted model |
AIC |
the (generalized) Akaike Information Criterion for |
Note
These functions are used in add1,
drop1 and step and that may be their
main use.
Author(s)
B. D. Ripley
References
Venables, W. N. and Ripley, B. D. (1997) Modern Applied Statistics with S-PLUS. New York: Springer (2nd ed).
See Also
deviance, add1, step
Examples
example(glm)
extractAIC(glm.D93)#>> 5 15.129