collinear

This function identifies predictors with r^2 above a given cut-off and
produces an index of predictors to be removed. The function takes a matrix or
data.frame of predictors, and the columns need to be ordered in terms of
importance - first column of any pair that are correlated is retained and
subsequent columns which correlate above the cut-off are flagged for removal.

Implements nested k*l-fold cross-validation for lasso and elastic-net regularised linear models via the 'glmnet' package and other machine learning models via the 'caret' package <doi:10.1093/bioadv/vbad048>. Cross-validation of 'glmnet' alpha mixing parameter and embedded fast filter functions for feature selection are provided. Described as double cross-validation by Stone (1977) <doi:10.1111/j.2517-6161.1977.tb01603.x>. Also implemented is a method using outer CV to measure unbiased model performance metrics when fitting Bayesian linear and logistic regression shrinkage models using the horseshoe prior over parameters to encourage a sparse model as described by Piironen & Vehtari (2017) <doi:10.1214/17-EJS1337SI>.

Myles Lewis

nestedcv

Nested Cross-Validation with 'glmnet' and 'caret'

Athina Spiliopoulou

Cankut Cubuk

David Rios Santini

Katriona Goldmann

Ryan C. Thompson

collinear function

<dl><dt>x</dt>
<dd>A matrix or data.frame of values. The order of columns is used to
determine which columns to retain, so the columns in <code>x</code> should be sorted
with the most important columns first.</dd>
<dt>rsq_cutoff</dt>
<dd>Value of cut-off for r-squared</dd>
<dt>rsq_method</dt>
<dd>character string indicating which correlation coefficient
is to be computed. One of "pearson" (default), "kendall", or "spearman".
See <code><a href="/link/cor()?package=nestedcv&version=0.9.0" data-mini-rdoc="nestedcv::cor()">cor()</a></code>.</dd>
<dt>verbose</dt>
<dd>Boolean whether to print details</dd></dl>

Arguments

Filter to reduce collinearity in predictors — collinear

<dl>

<dt>x</dt>
<dd>A matrix or data.frame of values. The order of columns is used to
determine which columns to retain, so the columns in <code>x</code> should be sorted
with the most important columns first.</dd>


<dt>rsq_cutoff</dt>
<dd>Value of cut-off for r-squared</dd>


<dt>rsq_method</dt>
<dd>character string indicating which correlation coefficient
is to be computed. One of "pearson" (default), "kendall", or "spearman".
See <code><a href='https://rdrr.io/r/stats/cor.html'>cor()</a></code>.</dd>


<dt>verbose</dt>
<dd>Boolean whether to print details</dd>

</dl>

collinear: Filter to reduce collinearity in predictors

Description

Usage

Value

Arguments