a b/man/posterior_predict.hsstan.Rd
1
% Generated by roxygen2: do not edit by hand
2
% Please edit documentation in R/postestimation.R
3
\name{posterior_predict.hsstan}
4
\alias{posterior_predict.hsstan}
5
\alias{posterior_predict}
6
\title{Posterior predictive distribution}
7
\usage{
8
\method{posterior_predict}{hsstan}(object, newdata = NULL, nsamples = NULL, seed = NULL, ...)
9
}
10
\arguments{
11
\item{object}{An object of class \code{hsstan}.}
12
13
\item{newdata}{Optional data frame containing the variables to use to
14
predict. If \code{NULL} (default), the model matrix is used. If
15
specified, its continuous variables should be standardized, since
16
the model coefficients are learnt on standardized data.}
17
18
\item{nsamples}{A positive integer indicating the number of posterior samples
19
to use. If \code{NULL} (default) all samples are used.}
20
21
\item{seed}{Optional integer defining the seed for the pseudo-random number
22
generator.}
23
24
\item{...}{Currently ignored.}
25
}
26
\value{
27
A matrix of size \code{S} by \code{N}, where \code{S} is the number of simulations from
28
the posterior predictive distribution, and \code{N} is the number of data points.
29
}
30
\description{
31
Draw from the posterior predictive distribution of the outcome.
32
}
33
\examples{
34
\dontshow{utils::example("hsstan", echo=FALSE)}
35
# continued from ?hsstan
36
posterior_predict(hs.biom)
37
38
}