sampler_control

Set computational options for the sampling algorithms

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

sampler_control function

<dl><dt>add.outer.R</dt>
<dd>whether to add the outer product of the constraint matrix for a better conditioned solve system
for blocks. This is done by default when using blocked Gibbs sampling for blocks with constraints.</dd>
<dt>recompute.e</dt>
<dd>when <code>FALSE</code>, residuals or linear predictors are only computed at the start of the simulation.
This may give a modest speedup but in some cases may be less accurate due to round-off error accumulation.
Default is <code>TRUE</code>.</dd>
<dt>CG</dt>
<dd>use a conjugate gradient iterative algorithm instead of Cholesky updates for sampling
the model's coefficients. This must be a list with possible components <code>max.it</code>,
<code>stop.criterion</code>, <code>verbose</code>, <code>preconditioner</code> and <code>scale</code>.
See the help for function <code>CG_control</code>, which can be used to specify these options.
Conjugate gradient sampling is currently an experimental feature that can be used for
blocked Gibbs sampling but with some limitations.</dd></dl>

Arguments

Set computational options for the sampling algorithms — sampler_control

<dl>

<dt>add.outer.R</dt>
<dd>whether to add the outer product of the constraint matrix for a better conditioned solve system
for blocks. This is done by default when using blocked Gibbs sampling for blocks with constraints.</dd>


<dt>recompute.e</dt>
<dd>when <code>FALSE</code>, residuals or linear predictors are only computed at the start of the simulation.
This may give a modest speedup but in some cases may be less accurate due to round-off error accumulation.
Default is <code>TRUE</code>.</dd>


<dt>CG</dt>
<dd>use a conjugate gradient iterative algorithm instead of Cholesky updates for sampling
the model's coefficients. This must be a list with possible components <code>max.it</code>,
<code>stop.criterion</code>, <code>verbose</code>, <code>preconditioner</code> and <code>scale</code>.
See the help for function <code>CG_control</code>, which can be used to specify these options.
Conjugate gradient sampling is currently an experimental feature that can be used for
blocked Gibbs sampling but with some limitations.</dd>

</dl>

sampler_control: Set computational options for the sampling algorithms

Description

Usage

Value

Arguments