RprobitB_latent_classes

print.RprobitB_latent_classes

This function creates an object of class <code>RprobitB_latent_classes</code> which
defines the number of latent classes and their updating scheme.

internal

Bayes estimation of probit choice models in cross-sectional and panel
settings. The package can analyze binary, multivariate, ordered, and ranked
choices, as well as heterogeneity of choice behavior among deciders. The
main functionality includes model fitting via Gibbs sampling, tools for
convergence diagnostic, choice data simulation, in-sample and out-of-sample
choice prediction, and model selection using information criteria and Bayes
factors. The latent class model extension facilitates preference-based
decider classification, where the number of latent classes can be inferred
via the Dirichlet process or a weight-based updating heuristic. This allows
for flexible modeling of choice behavior without the need to impose
structural constraints. For a reference on the method, see Oelschlaeger and
Bauer (2021) <https://trid.trb.org/view/1759753>.

Lennart Oelschläger

RprobitB

Bayesian Probit Choice Modeling

Dietmar Bauer

RprobitB_latent_classes function

<dl><dt>latent_classes</dt>
<dd>[<code><a href="/link/list()?package=RprobitB&version=1.2.0" data-mini-rdoc="RprobitB::list()">list()</a></code> | <code>NULL</code>] 
Optionally parameters specifying the number of latent classes and their
updating scheme. The values in brackets are the default.<ul>
<li><code>C</code> (<code>1</code>): The fixed number (greater or equal 1) of (initial) classes.</li>
<li><code>wb_update</code> (<code>FALSE</code>): Set to <code>TRUE</code> for weight-based class updates.</li>
<li><code>dp_update</code> (<code>FALSE</code>): Set to <code>TRUE</code> for Dirichlet process class updates.</li>
<li><code>Cmax</code> (<code>10</code>): The maximum number of latent classes.</li>
</ul></dd>The following specifications are used for the weight-based updating scheme:<ul>
<li><code>buffer</code> (<code>50</code>): The number of iterations to wait before the next update.</li>
<li><code>epsmin</code> (<code>0.01</code>): The threshold weight for removing a latent class.</li>
<li><code>epsmax</code> (<code>0.7</code>): The threshold weight for splitting a latent class.</li>
<li><code>deltamin</code> (<code>0.1</code>): The minimum mean distance before merging two classes.</li>
<li><code>deltashift</code> (<code>0.5</code>): The scale for shifting the class means after a split.</li>
</ul>
<dt>x</dt>
<dd>An object of class <code>RprobitB_latent_classes</code>.</dd>
<dt>...</dt>
<dd>Currently not used.</dd></dl>

Arguments

Create object of class RprobitB_latent_classes — RprobitB_latent_classes

<dl>

<dt>latent_classes</dt>
<dd>[<code><a href='https://rdrr.io/r/base/list.html'>list()</a></code> | <code>NULL</code>] 
Optionally parameters specifying the number of latent classes and their
updating scheme. The values in brackets are the default.<ul>
<li><code>C</code> (<code>1</code>): The fixed number (greater or equal 1) of (initial) classes.</li>
<li><code>wb_update</code> (<code>FALSE</code>): Set to <code>TRUE</code> for weight-based class updates.</li>
<li><code>dp_update</code> (<code>FALSE</code>): Set to <code>TRUE</code> for Dirichlet process class updates.</li>
<li><code>Cmax</code> (<code>10</code>): The maximum number of latent classes.</li>
</ul>

The following specifications are used for the weight-based updating scheme:<ul>
<li><code>buffer</code> (<code>50</code>): The number of iterations to wait before the next update.</li>
<li><code>epsmin</code> (<code>0.01</code>): The threshold weight for removing a latent class.</li>
<li><code>epsmax</code> (<code>0.7</code>): The threshold weight for splitting a latent class.</li>
<li><code>deltamin</code> (<code>0.1</code>): The minimum mean distance before merging two classes.</li>
<li><code>deltashift</code> (<code>0.5</code>): The scale for shifting the class means after a split.</li>
</ul></dd>


<dt>x</dt>
<dd>An object of class <code>RprobitB_latent_classes</code>.</dd>


<dt>...</dt>
<dd>Currently not used.</dd>

</dl>

RprobitB_latent_classes: Create object of class `RprobitB_latent_classes`

Description

Usage

Value

Arguments