choose.next

Return the index of the variable that should be added to the current model
according to the smallest KL-divergence (linear regression) or the largest
score test (logistic regression).

internal

Linear and logistic regression models penalized with hierarchical
shrinkage priors for selection of biomarkers (or more general variable
selection), which can be fitted using Stan (Carpenter et al. (2017)
<doi:10.18637/jss.v076.i01>). It implements the horseshoe and regularized
horseshoe priors (Piironen and Vehtari (2017) <doi:10.1214/17-EJS1337SI>),
as well as the projection predictive selection approach to recover a sparse
set of predictive biomarkers (Piironen, Paasiniemi and Vehtari (2020)
<doi:10.1214/20-EJS1711>).

Marco Colombo

hsstan

Hierarchical Shrinkage Stan Models for Biomarker Selection

Paul McKeigue

Athina Spiliopoulou

choose.next function

<dl><dt>x</dt>
<dd>Design matrix.</dd>
<dt>sigma2</dt>
<dd>Residual variance (1 for logistic regression).</dd>
<dt>fit</dt>
<dd>Matrix of fitted values for the full model.</dd>
<dt>fitp</dt>
<dd>Matrix of fitted values for the projected model.</dd>
<dt>chosen</dt>
<dd>Vector of indices of the columns of <code>x</code> in the current submodel.</dd>
<dt>is.logistic</dt>
<dd>Set to <code>TRUE</code> for a logistic regression model.</dd></dl>

Arguments

Next variable to enter the current submodel — choose.next

<dl>

<dt>x</dt>
<dd>Design matrix.</dd>


<dt>sigma2</dt>
<dd>Residual variance (1 for logistic regression).</dd>


<dt>fit</dt>
<dd>Matrix of fitted values for the full model.</dd>


<dt>fitp</dt>
<dd>Matrix of fitted values for the projected model.</dd>


<dt>chosen</dt>
<dd>Vector of indices of the columns of <code>x</code> in the current submodel.</dd>


<dt>is.logistic</dt>
<dd>Set to <code>TRUE</code> for a logistic regression model.</dd>

</dl>

choose.next: Next variable to enter the current submodel

Description

Usage

Arguments