\name{unmarkedMultFrame}
\alias{unmarkedMultFrame}
\alias{yearlySiteCovs}
\alias{yearlySiteCovs,unmarkedMultFrame-method}
\alias{yearlySiteCovs<-}
\alias{yearlySiteCovs<-,unmarkedMultFrame-method}
\title{Create an unmarkedMultFrame.}
\usage{unmarkedMultFrame(y, siteCovs, obsCovs, numPrimary, yearlySiteCovs)}
\description{This function constructs an unmarkedMultFrame object.}

\details{unmarkedMultFrame objects are used by
\code{\link{colext}}.

For a study with \emph{M} sites, \emph{T} years, and a maximum of
\emph{J} observations per site-year, the data are shaped as follows.
\code{y} is an \eqn{M \times TJ}{M by TJ} matrix, with each row
corresponding to a site.  \code{siteCovs} is a data frame with \eqn{M}
rows.  \code{yearlySiteCovs} is a data frame with \eqn{MT} rows which
are in site-major, year-minor order.  \code{obsCovs} is a data frame
with \eqn{MTJ} rows, which are ordered by site-year-observation, so that
a column of \code{obsCovs} corresponds to \command{as.vector(t(y))},
element-by-element.  The number of years must be specified in
\code{numPrimary}.

If the data are in long format, the convenience function
\code{\link{formatMult}} is useful for creating the unmarkedMultFrame.}

\value{an unmarkedFrame object}
\arguments{\item{y}{A matrix of the observed data.}
\item{siteCovs}{Data frame of covariates that vary at the site level.}
\item{obsCovs}{Data frame of covariates that vary within site-year-observation level.}
\item{numPrimary}{Number of primary time periods (seasons in the multiseason model).}
\item{yearlySiteCovs}{Data frame containing covariates at the site-year level.}}