logLik.eicm

Compute the (penalized) log-likelihood of the data matrix included in the EICM model,
or the log-likelihood of a new occurrence data matrix given the model.

Model fitting and species biotic interaction network topology selection for explicit
interaction community models. Explicit interaction community models are an extension of binomial
linear models for joint modelling of species communities, that incorporate both the effects of
species biotic interactions and the effects of missing covariates. Species interactions are modelled
as direct effects of each species on each of the others, and are estimated alongside the effects of
missing covariates, modelled as latent factors. The package includes a penalized maximum likelihood
fitting function, and a genetic algorithm for selecting the most parsimonious species interaction
network topology.

Miguel Porto

eicm

Explicit Interaction Community Models

Pedro Beja

logLik.eicm function

<dl><dt>object</dt>
<dd>a EICM model</dd>
<dt>occurrences</dt>
<dd>the occurrence data matrix. If omitted, the data matrix used to fit the model is used.</dd>
<dt>allow.na</dt>
<dd>logical. Allow NAs in the occurrence matrix? If no NAs exist, it's faster to set to FALSE.</dd>
<dt>...</dt>
<dd>additional argument(s) for methods.</dd></dl>

Arguments

EICM (penalized) log-likelihood — logLik.eicm

<dl>

<dt>object</dt>
<dd>a EICM model</dd>


<dt>occurrences</dt>
<dd>the occurrence data matrix. If omitted, the data matrix used to fit the model is used.</dd>


<dt>allow.na</dt>
<dd>logical. Allow NAs in the occurrence matrix? If no NAs exist, it's faster to set to FALSE.</dd>


<dt>...</dt>
<dd>additional argument(s) for methods.</dd>

</dl>

logLik.eicm: EICM (penalized) log-likelihood

Description

Usage

Value

Arguments