R/densLPS_object.R

In DALSM: Nonparametric Double Additive Location-Scale Model (DALSM)

#' Object generated by function \code{densityLPS}
#'
#' @description An object returned by function \code{\link{densityLPS}}: this is a list
#' with various components related to the estimation of a density with given mean and variance from potentially right- or interval-censored data using Laplace P-splines.
#'
#' @return An object returned by \code{\link{densityLPS}} has the following elements:
#' Essential part:
#' \itemize{
#' \item{\code{converged} : \verb{ }}{logical convergence indicator.}
#' \item{\code{ddist} : \verb{ }}{fitted density function.}
#' \item{\code{Hdist} : \verb{ }}{fitted cumulative hazard function.}
#' \item{\code{hdist} : \verb{ }}{fitted hazard function.}
#' \item{\code{pdist} : \verb{ }}{fitted cumulative distribution function.}
#' \item{\code{ymin, ymax} : \verb{ }}{assumed values for the support of the distribution.}
#' \item{\code{phi} : \verb{ }}{estimated B-spline coefficients for the log-hazard of the error distribution.}
#' \item{\code{U.phi} : \verb{ }}{score of the Lagrangian G(\eqn{\phi|\omega}).}
#' \item{\code{tau}, \code{ltau} : \verb{ }}{selected penalty parameter and its logarithm.}
#' \item{\code{est} : \verb{ }}{vector containing the estimated/selected (\eqn{\phi,\log\tau}) parameters.}
#' \item{\code{fixed.phi} : \verb{ }}{logical indicating whether the spline parameters were given fixed values or estimated from the data.}
#' \item{\code{phi.ref} : \verb{ }}{reference values for the spline parameters with respect to which \eqn{\phi} is compared during penalization.}
#' \item{\code{BWB} : \verb{ }}{Hessian for \eqn{\phi} without the penalty contribution.}
#' \item{\code{Prec} : \verb{ }}{Hessian or posterior precision matrix for \eqn{\phi}.}
#' \item{\code{Fisher} : \verb{ }}{Fisher information for \eqn{\phi}.}
#' \item{\code{bins, ugrid, du} : \verb{ }}{bins (of width 'du') and with midpoints 'ugrid' partitioning the support of the density.}
#' \item{\code{h.grid, H.grid, dens.grid} : \verb{ }}{hazard, cumulative hazard and density values at the grid midpoints 'ugrid'.}
#' \item{\code{h.bins, H.bins, dens.bins} : \verb{ }}{hazard, cumulative hazard and density values at the bin limits 'bins'.}
#' \item{\code{expected} : \verb{ }}{expected number of observations within each bin.}
#' \item{\code{Finfty} : \verb{ }}{integrated density value over the considered support.}
#' \item{\code{Mean0, Var0} : \verb{ }}{when specified, constrained mean and variance values during estimation.}
#' \item{\code{mean.dist, var.dist} : \verb{ }}{mean and variance of the fitted density.}
#' \item{\code{method} : \verb{ }}{method used for penaly selection: "evidence" (by maximizing the marginal posterior for \eqn{\tau}) or "Schall" (Schall's method).}
#' \item{\code{ed} : \verb{ }}{effective number of (spline) parameters.}
#' \item{\code{iterations} : \verb{ }}{total number of iterations necessary for convergence.}
#' \item{\code{elapsed.time} : \verb{ }}{time required for convergence.}
#' }
#' Additional elements:
#' the content of the \link{Dens1d.object} used when \link{densityLPS} was called.
#'
#' @author Philippe Lambert \email{p.lambert@uliege.be}
#' @references Lambert, P. (2021). Fast Bayesian inference using Laplace approximations
#' in nonparametric double additive location-scale models with right- and
#' interval-censored data.
#' \emph{Computational Statistics and Data Analysis}, 161: 107250.
#' <doi:10.1016/j.csda.2021.107250>
#'
#' @seealso \code{\link{densityLPS}}, \code{\link{DALSM}}
#'
#' @name densLPS.object
NULL