recalc.reStruct {nlme}R Documentation

Recalculate for an reStruct Object

Description

The log-likelihood, or restricted log-likelihood, of the Gaussian linear mixed-effects model represented by object and conLin (assuming spherical within-group covariance structure), evaluated at coef(object) is calculated and added to the logLik component of conLin. The settings attribute of object determines whether the log-likelihood, or the restricted log-likelihood, is to be calculated. The computational methods for the (restricted) log-likelihood calculations are described in Bates and Pinheiro (1998).

Usage

## S3 method for class 'reStruct':
recalc(object, conLin, ...)

Arguments

object an object inheriting from class reStruct, representing a random effects structure and consisting of a list of pdMat objects.
conLin a condensed linear model object, consisting of a list with components "Xy", corresponding to a regression matrix (X) combined with a response vector (y), and "logLik", corresponding to the log-likelihood of the underlying model.
... some methods for this generic require additional arguments. None are used in this method.

Value

the condensed linear model with its logLik component updated.

Author(s)

Jose Pinheiro Jose.Pinheiro@pharma.novartis.com and Douglas Bates bates@stat.wisc.edu

References

Bates, D.M. and Pinheiro, J.C. (1998) "Computational methods for multilevel models" available in PostScript or PDF formats at http://franz.stat.wisc.edu/pub/NLME/

See Also

reStruct, logLik, lme


[Package Contents]