Rev 5289 | Blame | Compare with Previous | Last modification | View Log | Download | RSS feed
\name{full.score}\alias{full.score}%- Also NEED an `\alias' for EACH other topic documented here.\title{GCV/UBRE score for use within nlm}\description{ Evaluates GCV/UBRE score for a GAM, given smoothingparameters. The routine calls \code{\link{gam.fit}} to fit the model, and isusually called by \code{\link{nlm}} to optimize the smoothing parameters.This is basically a service routine for \code{\link{gam}}, and is not usuallycalled directly by users. It is only used in this context for GAMs fitted byouter iteration (see \code{\link{gam.outer}}) when the the outer method is\code{"nlm.fd"} (see \code{\link{gam}} argument \code{optimizer}).}\usage{full.score(sp,G,family,control,gamma,...)}%- maybe also `usage' for other objects documented here.\arguments{\item{sp}{The logs of the smoothing parameters}\item{G}{a list returned by \code{mgcv:::gam.setup}}\item{family}{The family object for the GAM.}\item{control}{a list returned be \code{\link{gam.control}}}\item{gamma}{the degrees of freedom inflation factor (usually 1).}\item{...}{other arguments, typically for passing on to \code{gam.fit}.}}\value{ The value of the GCV/UBRE score, with attribute \code{"full.gam.object"}which is the full object returned by \code{\link{gam.fit}}.}\author{ Simon N. Wood \email{simon.wood@r-project.org}}\keyword{models} \keyword{smooth} \keyword{regression}%-- one or more ..