abess_mmlt

Optimal subset selection for multivariate transformation models

Greedy optimal subset selection for transformation models
(Hothorn et al., 2018, <doi:10.1111/sjos.12291> ) based on the abess
algorithm (Zhu et al., 2020, <doi:10.1073/pnas.2014241117> ). Applicable to
models from packages 'tram' and 'cotram'. Application to shift-scale
transformation models are described in Siegfried et al. (2024,
<doi:10.1080/00031305.2023.2203177>).

Lucas Kook

tramvs

Optimal Subset Selection for Transformation Models

Sandra Siegfried

Torsten Hothorn

abess_mmlt function

<dl><dt>mltargs</dt>
<dd>Arguments passed to <code>mmlt</code></dd>
<dt>supp</dt>
<dd>support size of the coefficient vector</dd>
<dt>k_max</dt>
<dd>maximum support size to consider during the splicing algorithm.
Defaults to <code>supp</code>.</dd>
<dt>thresh</dt>
<dd>threshold when to stop splicing. Defaults to
0.01 * <code>supp</code> * p * log(log(n)) / n$, where p denotes the number of predictors
and n the sample size.</dd>
<dt>init</dt>
<dd>initialize active set. Defaults to <code>TRUE</code> and initializes the
active set with those covariates that are most correlated with score residuals
of an unconditional <code>modFUN(update(formula, . ~ 1))</code>.</dd>
<dt>m_max</dt>
<dd>maximum number of iterating the splicing algorithm.</dd>
<dt>m0</dt>
<dd>Transformation model for initialization</dd>
<dt>...</dt>
<dd>Currently ignored</dd></dl>

Arguments

Optimal subset selection for multivariate transformation models — abess_mmlt

<dl>

<dt>mltargs</dt>
<dd>Arguments passed to <code>mmlt</code></dd>


<dt>supp</dt>
<dd>support size of the coefficient vector</dd>


<dt>k_max</dt>
<dd>maximum support size to consider during the splicing algorithm.
Defaults to <code>supp</code>.</dd>


<dt>thresh</dt>
<dd>threshold when to stop splicing. Defaults to
0.01 * <code>supp</code> * p * log(log(n)) / n$, where p denotes the number of predictors
and n the sample size.</dd>


<dt>init</dt>
<dd>initialize active set. Defaults to <code>TRUE</code> and initializes the
active set with those covariates that are most correlated with score residuals
of an unconditional <code>modFUN(update(formula, . ~ 1))</code>.</dd>


<dt>m_max</dt>
<dd>maximum number of iterating the splicing algorithm.</dd>


<dt>m0</dt>
<dd>Transformation model for initialization</dd>


<dt>...</dt>
<dd>Currently ignored</dd>

</dl>

abess_mmlt: Optimal subset selection for multivariate transformation models

Description

Usage

Value

Arguments