setup_lambda

Extremely efficient procedures for fitting regularization path with l0, l1, and truncated lasso penalty for linear regression and logistic regression models. This version is a completely new version compared with our previous version, which was mainly based on R. New core algorithms are developed and are now written in C++ and highly optimized.

Yu Yang

glmtlp

Generalized Linear Models with Truncated Lasso Penalty

Chunlin Li

Chong Wu

Xiaotong Shen

Wei Pan

setup_lambda function

<dl><dt>X</dt>
<dd>Input matrix, of dimension <code>nobs</code> x <code>nvars</code>; 
each row is an observation vector.</dd>
<dt>y</dt>
<dd>Response variable, of length <code>nobs</code>. For <code>family="gaussian"</code>, 
it should be quantitative; for <code>family="binomial"</code>, it should be either 
a factor with two levels or a binary vector.</dd>
<dt>weights</dt>
<dd>Observation weights.</dd>
<dt>lambda.min.ratio</dt>
<dd>The smallest value for <code>lambda</code>, as a fraction of 
<code>lambda.max</code>, the smallest value for which all coefficients are zero. 
The default depends on the sample size <code>nobs</code> relative to the number 
of variables <code>nvars</code>.</dd>
<dt>nlambda</dt>
<dd>The number of <code>lambda</code> values.</dd></dl>

Arguments

Generate lambda sequence. — setup_lambda

<dl>

<dt>X</dt>
<dd>Input matrix, of dimension <code>nobs</code> x <code>nvars</code>; 
each row is an observation vector.</dd>


<dt>y</dt>
<dd>Response variable, of length <code>nobs</code>. For <code>family="gaussian"</code>, 
it should be quantitative; for <code>family="binomial"</code>, it should be either 
a factor with two levels or a binary vector.</dd>


<dt>weights</dt>
<dd>Observation weights.</dd>


<dt>lambda.min.ratio</dt>
<dd>The smallest value for <code>lambda</code>, as a fraction of 
<code>lambda.max</code>, the smallest value for which all coefficients are zero. 
The default depends on the sample size <code>nobs</code> relative to the number 
of variables <code>nvars</code>.</dd>


<dt>nlambda</dt>
<dd>The number of <code>lambda</code> values.</dd>

</dl>

Generate lambda sequence.

setup_lambda: Generate lambda sequence.

Description

Usage

Arguments