BIC.logLik {nlme} | R Documentation |
This function calculates the Bayesian information criterion,
also known as Schwarz's Bayesian criterion (SBC) for an object
inheriting from class logLik
, according to the formula
log-likelihood +
npar*log(nobs), where npar represents the number of
parameters and nobs the number of observations in the
fitted model. When comparing fitted objects, the smaller the BIC, the
better the fit.
BIC(object, ...)
object |
an object inheriting from class logLik , usually
resulting from applying a logLik method to a fitted model
object. |
... |
some methods for this generic use optional arguments. None are used in this method. |
a numeric value with the corresponding BIC.
Jose Pinheiro Jose.Pinheiro@pharma.novartis.com and Douglas Bates bates@stat.wisc.edu
Schwarz, G. (1978) "Estimating the Dimension of a Model", Annals of Statistics, 6, 461-464.
data(Orthodont) fm1 <- lm(distance ~ age, data = Orthodont) BIC(logLik(fm1))