conditional_gmrf

Generates samples from a Gaussian Markov random field (GMRF) conditional upon
fixed values for some elements.

Fits a wide variety of multivariate spatio-temporal models
with simultaneous and lagged interactions among variables (including
vector autoregressive spatio-temporal ('VAST') dynamics)
for areal, continuous, or network spatial domains.
It includes time-variable, space-variable, and space-time-variable
interactions using dynamic structural equation models ('DSEM')
as expressive interface, and the 'mgcv' package to specify splines
via the formula interface. See Thorson et al. (2024)
<doi:10.48550/arXiv.2401.10193> for more details.

James Thorson

tinyVAST

Multivariate Spatio-Temporal Models using Structural Equations

conditional_gmrf function

<dl><dt>Q</dt>
<dd>precision for a zero-centered GMRF.</dd>
<dt>observed_idx</dt>
<dd>integer vector listing rows of <code>Q</code> corresponding to
fixed measurements</dd>
<dt>x_obs</dt>
<dd>numeric vector with fixed values for indices <code>observed_idx</code></dd>
<dt>n_sims</dt>
<dd>integer listing number of simulated values</dd>
<dt>what</dt>
<dd>Whether to simulate from the conditional GMRF, or predict the mean
and precision</dd></dl>

Arguments

Conditional simulation from a GMRF — conditional_gmrf

<dl>

<dt>Q</dt>
<dd>precision for a zero-centered GMRF.</dd>


<dt>observed_idx</dt>
<dd>integer vector listing rows of <code>Q</code> corresponding to
fixed measurements</dd>


<dt>x_obs</dt>
<dd>numeric vector with fixed values for indices <code>observed_idx</code></dd>


<dt>n_sims</dt>
<dd>integer listing number of simulated values</dd>


<dt>what</dt>
<dd>Whether to simulate from the conditional GMRF, or predict the mean
and precision</dd>

</dl>

conditional_gmrf: Conditional simulation from a GMRF

Description

Usage

Value

Arguments