Gmcmc

Performs Markov Chain Monte Carlo (MCMC) sampling on a graph model.

Implements state-of-the-art Random Graphical Models (RGMs) for multivariate data analysis across multiple environments, offering tools for exploring network interactions and structural relationships. Capabilities include joint inference across environments, integration of external covariates, and a Bayesian framework for uncertainty quantification. Applicable in various fields, including microbiome analysis. Methods based on Vinciotti, V., Wit, E., & Richter, F. (2023). "Random Graphical Model of Microbiome Interactions in Related Environments." <arXiv:2304.01956>.

Francisco Richter

Advanced Inference with Random Graphical Models

Veronica Vinciotti

Ernst Wit

Gmcmc function

<dl><dt>G</dt>
<dd>Graph adjacency matrix.</dd>
<dt>X</dt>
<dd>Optional matrix of covariates.</dd>
<dt>iter</dt>
<dd>Number of MCMC iterations to perform.</dd>
<dt>alpha</dt>
<dd>Initial values for alpha parameters.</dd>
<dt>theta</dt>
<dd>Initial values for theta parameters.</dd>
<dt>loc</dt>
<dd>Initial locations for nodes in the graph.</dd>
<dt>burnin</dt>
<dd>Number of burn-in iterations.</dd></dl>

Arguments

Graph MCMC Sampler — Gmcmc

<dl>

<dt>G</dt>
<dd>Graph adjacency matrix.</dd>


<dt>X</dt>
<dd>Optional matrix of covariates.</dd>


<dt>iter</dt>
<dd>Number of MCMC iterations to perform.</dd>


<dt>alpha</dt>
<dd>Initial values for alpha parameters.</dd>


<dt>theta</dt>
<dd>Initial values for theta parameters.</dd>


<dt>loc</dt>
<dd>Initial locations for nodes in the graph.</dd>


<dt>burnin</dt>
<dd>Number of burn-in iterations.</dd>

</dl>

Gmcmc: Graph MCMC Sampler

Description

Usage

Value

Arguments