Package edu.cmu.tetrad.regression

Class LogisticRegression

java.lang.Object

edu.cmu.tetrad.regression.LogisticRegression

All Implemented Interfaces:

TetradSerializable, Serializable

public class LogisticRegression
extends Object
implements TetradSerializable

Implements a logistic regression algorithm based on a Javascript implementation by John Pezzullo. That implementation together with a description of logistic regression and some examples appear on his web page ...

See also Applied Logistic Regression, by D.W. Hosmer and S. Lemeshow. 1989, John Wiley and Sons, New York which Pezzullo references. In particular see pages 27-29.

Version:

$Id: $Id

Author:

Frank Wimberly

See Also:

• Serialized Form

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
static class	LogisticRegression.Result	The result of a logistic regression.

Constructor Summary

Constructors

Constructor	Description
LogisticRegression(DataSet dataSet)	A mixed data set.

Method Summary

Modifier and Type	Method	Description
double	getAlpha()	Getter for the field alpha.
LogisticRegression.Result	regress(DiscreteVariable x, List<Node> regressors)	x must be binary; regressors must be continuous or binary.
static LogisticRegression	serializableInstance()	Generates a simple exemplar of this class to test serialization.
void	setAlpha(double alpha)	Sets the alpha level.
void	setRows(int[] rows)	Setter for the field rows.

Methods inherited from class java.lang.Object

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

Constructor Details

LogisticRegression

public LogisticRegression(DataSet dataSet)

A mixed data set. The targets of regresson must be binary. Regressors must be continuous or binary. Other variables don't matter.

Parameters:

dataSet - a DataSet object

Method Details

serializableInstance

public static LogisticRegression serializableInstance()

Generates a simple exemplar of this class to test serialization.

Returns:

a LogisticRegression object

regress

public LogisticRegression.Result regress(DiscreteVariable x,
 List<Node> regressors)

x must be binary; regressors must be continuous or binary.

Parameters:

x - a DiscreteVariable object

regressors - a List object

Returns:

a LogisticRegression.Result object

getAlpha

public double getAlpha()

Getter for the field alpha.

Returns:

the alpha level.

setAlpha

public void setAlpha(double alpha)

Sets the alpha level.

Parameters:

alpha - a double

setRows

public void setRows(int[] rows)

Setter for the field rows.

Parameters:

rows - an array of objects