dev.nm.stat.regression.linear.lasso.lars

Class LARSFitting

java.lang.Object

dev.nm.stat.regression.linear.lasso.lars.LARSFitting

public class LARSFitting
extends Object

This class computes the entire LARS sequence of coefficients and fits, starting from zero to the OLS fit.

See Also:

• B. Efron et. al, "Least Angle Regression," The Annals of Statistics, Volume: 32(2), 407 - 499, 2004.
• T. Hastie, R. Tibshirani and J. Friedman, "The Elements of Statistical Learning: Data Mining, Inference, and Prediction (Second Edition)," New York, Springer-Verlag, 2009.
• Wikipedia: Least angle regression

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	LARSFitting.Estimators

Constructor Summary

Constructors

Constructor and Description
LARSFitting(LARSProblem problem) Estimates the entire LARS sequence of coefficients with the default epsilon and maximum number of steps.
LARSFitting(LARSProblem problem, double epsilon, int maxIterations) Estimates the entire LARS sequence of coefficients and fits, starting from zero to the OLS fit.
LARSFitting(LARSProblem problem, int maxIterations) Estimates the entire LARS sequence of coefficients with the default epsilon.

Method Summary

Modifier and Type	Method and Description
LARSFitting.Estimators	getEstimators() Calculate the LARS fitting estimators.

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Detail

LARSFitting

public LARSFitting(LARSProblem problem,
                   double epsilon,
                   int maxIterations)

Estimates the entire LARS sequence of coefficients and fits, starting from zero to the OLS fit.

Parameters:

problem - the LARS problem to be solved

epsilon - a precision parameter: when a number |x| ≤ ε, it is considered 0

maxIterations - the maximum number of iterations

LARSFitting

public LARSFitting(LARSProblem problem,
                   int maxIterations)

Estimates the entire LARS sequence of coefficients with the default epsilon.

Parameters:

problem - the LARS problem

maxIterations - the maximum number of steps taken

LARSFitting

public LARSFitting(LARSProblem problem)

Estimates the entire LARS sequence of coefficients with the default epsilon and maximum number of steps.

Parameters:

problem - the LARS problem

Method Detail

getEstimators

public LARSFitting.Estimators getEstimators()

Calculate the LARS fitting estimators.

Returns:

the LARS fitting estimators