pibble_sim

Simulate simple pibble dataset and priors (for testing)

Provides methods for fitting and inspection of Bayesian Multinomial Logistic Normal Models using MAP estimation
and Laplace Approximation as developed in Silverman et. Al. (2022) <https://www.jmlr.org/papers/v23/19-882.html>. Key functionality is implemented in C++ for
scalability. 'fido' replaces the previous package 'stray'.

Michelle Nixon

fido

Bayesian Multinomial Logistic Normal Regression

Justin Silverman

Kim Roche

pibble_sim function

<dl><dt>D</dt>
<dd>number of multinomial categories</dd>
<dt>N</dt>
<dd>number of samples</dd>
<dt>Q</dt>
<dd>number of covariates (first one is an intercept, must be &gt; 1)</dd>
<dt>use_names</dt>
<dd>should samples, covariates, and categories be named</dd>
<dt>true_priors</dt>
<dd>should Xi and upsilon be chosen to have mean at true 
simulated value</dd></dl>

Arguments

Simulate simple pibble dataset and priors (for testing) — pibble_sim

<dl>

<dt>D</dt>
<dd>number of multinomial categories</dd>


<dt>N</dt>
<dd>number of samples</dd>


<dt>Q</dt>
<dd>number of covariates (first one is an intercept, must be &gt; 1)</dd>


<dt>use_names</dt>
<dd>should samples, covariates, and categories be named</dd>


<dt>true_priors</dt>
<dd>should Xi and upsilon be chosen to have mean at true 
simulated value</dd>

</dl>

pibble_sim: Simulate simple pibble dataset and priors (for testing)

Description

Usage

Value

Arguments

Examples