correlation

Element 'factor' of a model component is a formula composed of several possible terms described below.
It is used to derive a (sparse) precision matrix for a set of coefficient, and possibly a matrix representing
a set of linear constraints to be imposed on the coefficient vector.<dl class="dl-horizontal">
 <dt>iid(f)</dt><dd>Independent effects corresponding to the levels of factor <code>f</code>.</dd>
 <dt>RW1(f, circular=FALSE)</dt><dd>First-order random walk.</dd>
 <dt>RW2(f)</dt><dd>Second-order random walk.</dd>
 <dt>AR1(f, phi)</dt><dd>First-order autoregressive correlation structure among the levels of <code>f</code>.
 Required argument <code>phi</code> (fixed number for now).</dd>
 <dt>season(f, period)</dt><dd>Dummy seasonal with period <code>period</code>.</dd>
 <dt>spatial(f, poly.df, snap, queen, derive.constraints=FALSE)</dt><dd>CAR spatial correlation.
 Argument <code>poly.df</code> should be an object of class <code>SpatialPolygonsDataFrame</code> obtained
 e.g. from reading in a shape file with <code><a rd-options="maptools" href="/link/readShapeSpatial?package=mcmcsae&version=0.6.0&to=maptools" data-mini-rdoc="maptools::readShapeSpatial">readShapeSpatial</a></code> from
 package maptools. Arguments <code>snap</code> and <code>queen</code> are passed to <code><a rd-options="spdep" href="/link/poly2nb?package=mcmcsae&version=0.6.0&to=spdep" data-mini-rdoc="spdep::poly2nb">poly2nb</a></code>.
 If <code>derive.constraints=TRUE</code> the constraint matrix for an IGMRF model component
 is formed by computing the singular vectors of the precision matrix.</dd>
 <dt>custom(f, QD)</dt><dd>A custom precision or incidence matrix associated with factor f can be passed to argument <code>QD</code>.</dd>
</dl>

Fit multi-level models with possibly correlated
random effects using Markov Chain Monte Carlo simulation.
Such models allow smoothing over space and time and are useful in,
for example, small area estimation.

Harm Jan Boonstra

mcmcsae

Markov Chain Monte Carlo Small Area Estimation

Grzegorz Baltissen

correlation function

Element 'factor' of a model component is a formula composed of several possible terms described below.
It is used to derive a (sparse) precision matrix for a set of coefficient, and possibly a matrix representing
a set of linear constraints to be imposed on the coefficient vector.<dl class='dl-horizontal'>
 <dt>iid(f)</dt><dd>Independent effects corresponding to the levels of factor <code>f</code>.</dd>
 <dt>RW1(f, circular=FALSE)</dt><dd>First-order random walk.</dd>
 <dt>RW2(f)</dt><dd>Second-order random walk.</dd>
 <dt>AR1(f, phi)</dt><dd>First-order autoregressive correlation structure among the levels of <code>f</code>.
 Required argument <code>phi</code> (fixed number for now).</dd>
 <dt>season(f, period)</dt><dd>Dummy seasonal with period <code>period</code>.</dd>
 <dt>spatial(f, poly.df, snap, queen, derive.constraints=FALSE)</dt><dd>CAR spatial correlation.
 Argument <code>poly.df</code> should be an object of class <code>SpatialPolygonsDataFrame</code> obtained
 e.g. from reading in a shape file with <code><a rd-options='maptools' href='readShapeSpatial'>readShapeSpatial</a></code> from
 package maptools. Arguments <code>snap</code> and <code>queen</code> are passed to <code><a rd-options='spdep' href='poly2nb'>poly2nb</a></code>.
 If <code>derive.constraints=TRUE</code> the constraint matrix for an IGMRF model component
 is formed by computing the singular vectors of the precision matrix.</dd>
 <dt>custom(f, QD)</dt><dd>A custom precision or incidence matrix associated with factor f can be passed to argument <code>QD</code>.</dd>
</dl>

correlation: Correlation structures

Description

Arguments