com.numericalmethod.suanshu.stats.regression.linear.glm
Class Residuals

java.lang.Object
  com.numericalmethod.suanshu.stats.regression.linear.Residuals
      com.numericalmethod.suanshu.stats.regression.linear.glm.Residuals

Direct Known Subclasses:

Residuals

public class Residuals
extends Residuals

Residual analysis of the results of a Generalized Linear Model regression.

Overdispersion occurs when the observed variance of the data is larger than the predicted variance.

Deviance measures the goodness-of-fit of a model

Field Summary

double	deviance deviance
ImmutableVector	devianceResiduals deviances residuals
protected double[]	deviances deviances of observations
double	overdispersion overdispersion

Fields inherited from class com.numericalmethod.suanshu.stats.regression.linear.Residuals

fitted, problem, residuals

Constructor Summary

protected

Residuals(GlmProblem problem, Vector fitted) Perform the residual analysis for a GLM problem.

Method Summary

double[]	deviances()
double	overdispersion() Compute the overdispersion of this GLM.

Methods inherited from class java.lang.Object

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

Field Detail

overdispersion

public final double overdispersion

overdispersion

deviance

public final double deviance

deviance

deviances

protected final double[] deviances

deviances of observations

devianceResiduals

public final ImmutableVector devianceResiduals

deviances residuals

Constructor Detail

Residuals

protected Residuals(GlmProblem problem,
                    Vector fitted)

Perform the residual analysis for a GLM problem.

Parameters:

problem - the GLM problem to be solved

fitted - the fitted values

Method Detail

overdispersion

public double overdispersion()

Compute the overdispersion of this GLM.

Returns:

the overdispersion

deviances

public double[] deviances()