compute_probs_all

Compute category probabilities for all draws

internal

Fits cumulative link models (CLMs) for ordinal categorical data
using 'CmdStanR'. Supports various link functions including logit, probit,
cloglog, loglog, cauchit, and flexible parametric links such as
Generalized Extreme Value (GEV), Asymmetric Exponential Power (AEP),
and Symmetric Power. Models are pre-compiled using the 'instantiate'
package for fast execution without runtime compilation. Methods are
described in Agresti (2010, ISBN:978-0-470-08289-8),
Wang and Dey (2011) <doi:10.1007/s10651-010-0154-8>, and
Naranjo, Perez, and Martin (2015) <doi:10.1007/s11222-014-9449-1>.

Tomotaka Momozaki

clmstan

Cumulative Link Models with 'CmdStanR'

compute_probs_all function

<dl><dt>draws</dt>
<dd>Output from extract_prediction_draws()</dd>
<dt>X</dt>
<dd>Design matrix (N x P)</dd>
<dt>link</dt>
<dd>Link function name</dd>
<dt>base_link_param</dt>
<dd>Fixed link parameters</dd>
<dt>K</dt>
<dd>Number of categories</dd>
<dt>full</dt>
<dd>Whether link parameters were estimated</dd></dl>

Arguments

Compute category probabilities for all draws — compute_probs_all

<dl>

<dt>draws</dt>
<dd>Output from extract_prediction_draws()</dd>


<dt>X</dt>
<dd>Design matrix (N x P)</dd>


<dt>link</dt>
<dd>Link function name</dd>


<dt>base_link_param</dt>
<dd>Fixed link parameters</dd>


<dt>K</dt>
<dd>Number of categories</dd>


<dt>full</dt>
<dd>Whether link parameters were estimated</dd>

</dl>

compute_probs_all: Compute category probabilities for all draws

Description

Usage

Value

Arguments