coef.LarsPath

Compute coefficients at a given level of penalty

Algorithms for lasso and fused-lasso problems: C++ implementation of
the 'lars' algorithm for lasso and fusion penalization
<doi:10.1214/009053604000000067>, and EM-based
algorithms for (logistic) lasso and fused-lasso penalization.

Quentin Grimonprez

HDPenReg

High-Dimensional Penalized Regression

Serge Iovleff

coef.LarsPath function

<dl><dt>object</dt>
<dd>a LarsParth object</dd>
<dt>index</dt>
<dd>If mode ="norm", index represents the l1-norm of the coefficients with which we want to predict.
 If mode="fraction", index represents the ratio
(l1-norm of the coefficients with which we want to predict)/(l1-norm maximal of the LarsPath object).
 If mode="lambda", index represents the value of the penalty parameter. If mode="step", index represents the step number
 at which we want coefficients.</dd>
<dt>mode</dt>
<dd>"fraction" or "norm" or "lambda" or "step".</dd>
<dt>...</dt>
<dd>other arguments. Not used</dd></dl>

Arguments

Author

Compute coefficients — coef.LarsPath

<dl>

<dt>object</dt>
<dd>a LarsParth object</dd>


<dt>index</dt>
<dd>If mode ="norm", index represents the l1-norm of the coefficients with which we want to predict.
 If mode="fraction", index represents the ratio
(l1-norm of the coefficients with which we want to predict)/(l1-norm maximal of the LarsPath object).
 If mode="lambda", index represents the value of the penalty parameter. If mode="step", index represents the step number
 at which we want coefficients.</dd>


<dt>mode</dt>
<dd>"fraction" or "norm" or "lambda" or "step".</dd>


<dt>...</dt>
<dd>other arguments. Not used</dd>

</dl>

coef.LarsPath: Compute coefficients

Description

Usage

Value

Arguments

Author

See Also

Examples