sscden.Rd
\name{sscden}
\alias{sscden}
\alias{sscden1}
\title{Estimating Conditional Probability Density Using Smoothing
Splines}
\description{
Estimate conditional probability densities using smoothing spline
ANOVA models. The symbolic model specification via \code{formula}
follows the same rules as in \code{\link{lm}}.
}
\usage{
sscden(formula, response, type=NULL, data=list(), weights, subset,
na.action=na.omit, alpha=1.4, id.basis=NULL, nbasis=NULL,
seed=NULL, ydomain=as.list(NULL), yquad=NULL, prec=1e-7,
maxiter=30, skip.iter=FALSE)
sscden1(formula, response, type=NULL, data=list(), weights, subset,
na.action=na.omit, alpha=1.4, id.basis=NULL, nbasis=NULL,
seed=NULL, rho=list("xy"), ydomain=as.list(NULL), yquad=NULL,
prec=1e-7, maxiter=30, skip.iter=FALSE)
}
\arguments{
\item{formula}{Symbolic description of the model to be fit.}
\item{response}{Formula listing response variables.}
\item{type}{List specifying the type of spline for each variable.
See \code{\link{mkterm}} for details.}
\item{data}{Optional data frame containing the variables in the
model.}
\item{weights}{Optional vector of counts for duplicated data.}
\item{subset}{Optional vector specifying a subset of observations
to be used in the fitting process.}
\item{na.action}{Function which indicates what should happen when
the data contain NAs.}
\item{alpha}{Parameter defining cross-validation scores for
smoothing parameter selection.}
\item{id.basis}{Index of observations to be used as "knots."}
\item{nbasis}{Number of "knots" to be used. Ignored when
\code{id.basis} is specified.}
\item{seed}{Seed to be used for the random generation of "knots."
Ignored when \code{id.basis} is specified.}
\item{ydomain}{Data frame specifying marginal support of conditional
density.}
\item{yquad}{Quadrature for calculating integral on Y domain.
Mandatory if response variables other than factors or numerical
vectors are involved.}
\item{prec}{Precision requirement for internal iterations.}
\item{maxiter}{Maximum number of iterations allowed for
internal iterations.}
\item{skip.iter}{Flag indicating whether to use initial values of
theta and skip theta iteration. See \code{\link{ssanova}} for
notes on skipping theta iteration.}
\item{rho}{rho function needed for sscden1.}
}
\details{
The model is specified via \code{formula} and \code{response}, where
\code{response} lists the response variables. For example,
\code{sscden(~y*x,~y)} prescribe a model of the form
\deqn{
log f(y|x) = g_{y}(y) + g_{xy}(x,y) + C(x)
}
with the terms denoted by \code{"y"}, \code{"y:x"}; the term(s) not
involving response(s) are removed and the constant \code{C(x)} is
determined by the fact that a conditional density integrates to one
on the \code{y} axis. \code{sscden1} does keep terms not involving
response(s) during estimation, although those terms cancel out when
one evaluates the estimated conditional density.
The model terms are sums of unpenalized and penalized
terms. Attached to every penalized term there is a smoothing
parameter, and the model complexity is largely determined by the
number of smoothing parameters.
A subset of the observations are selected as "knots." Unless
specified via \code{id.basis} or \code{nbasis}, the number of
"knots" \eqn{q} is determined by \eqn{max(30,10n^{2/9})}, which is
appropriate for the default cubic splines for numerical vectors.
}
\note{
Default quadrature on the Y domain will be constructed for numerical
vectors on a hyper cube, then outer product with factor levels will
be taken if factors are involved. The sides of the hyper cube are
specified by \code{ydomain}; for \code{ydomain$y} missing, the default
is \code{c(min(y),max(y))+c(-1,1)*(max(y)-mimn(y))*.05}.
On a 1-D interval, the quadrature is the 200-point Gauss-Legendre
formula returned from \code{\link{gauss.quad}}. For multiple
numerical vectors, delayed Smolyak cubatures from
\code{\link{smolyak.quad}} are used on cubes with the marginals
properly transformed; see Gu and Wang (2003) for the marginal
transformations.
The results may vary from run to run. For consistency, specify
\code{id.basis} or set \code{seed}.
For reasonable execution time in high dimensions, set
\code{skip.iter=TRUE}.
}
\value{
\code{sscden} returns a list object of class \code{"sscden"}.
\code{sscden1} returns a list object of class
\code{c("sscden1","sscden")}.
\code{\link{dsscden}} and \code{\link{cdsscden}} can be used to
evaluate the estimated conditional density \eqn{f(y|x)} and
\eqn{f(y1|x,y2)}; \code{\link{psscden}}, \code{\link{qsscden}},
\code{\link{cpsscden}}, and \code{\link{cqsscden}} can be used to
evaluate conditional cdf and quantiles. The methods
\code{\link{project.sscden}} or \code{\link{project.sscden1}} can
be used to calculate the Kullback-Leibler or square-error
projections for model selection.
}
\references{
Gu, C. (1995), Smoothing spline density estimation: Conditional
distribution. \emph{Statistica Sinica}, \bold{5}, 709--726.
Springer-Verlag.
Gu, C. (2014), Smoothing Spline ANOVA Models: R Package gss.
\emph{Journal of Statistical Software}, 58(5), 1-25. URL
http://www.jstatsoft.org/v58/i05/.
}
\examples{
data(penny); set.seed(5732)
fit <- sscden1(~year*mil,~mil,data=penny,
ydomain=data.frame(mil=c(49,61)))
yy <- 1944+(0:92)/2
quan <- qsscden(fit,c(.05,.25,.5,.75,.95),
data.frame(year=yy))
plot(penny$year+.1*rnorm(90),penny$mil,ylim=c(49,61))
for (i in 1:5) lines(yy,quan[i,])
## Clean up
\dontrun{rm(penny,yy,quan)}
}
\keyword{smooth}
\keyword{models}
\keyword{distribution}