com.numericalmethod.suanshu.stats.regression.linear.ols
Class InformationCriteria

java.lang.Object
  com.numericalmethod.suanshu.stats.regression.linear.ols.InformationCriteria

public class InformationCriteria
extends java.lang.Object

The information criteria measure the goodness of fit of an estimated statistical model. The information criteria (IC) are not tests of the model in the sense of hypothesis testing; rather they are tests between models - a tool for model selection. Given a data set, several competing models may be ranked according to their IC, with the one having the lowest IC being the best. From the IC value one may infer that e.g. the top three models are in a tie and the rest are far worse, but it would be arbitrary to assign a value above which a given model is 'rejected'.

Akaike's information criterion is a measure of the goodness of fit of an estimated statistical model. It is grounded in the concept of entropy, in effect offering a relative measure of the information lost when a given model is used to describe reality and can be said to describe the tradeoff between bias and variance in model construction, or loosely speaking that of accuracy and complexity of the model.

The BIC is very closely related to the Akaike information criterion (AIC). In BIC, the penalty for additional parameters is stronger than that of the AIC.

See Also:

• Wikipedia: Akaike information criterion
• Wikipedia: Bayesian information criterion

Field Summary

double	AIC Akaike information criterion
double	BIC Bayesian information criterion

Method Summary

Methods inherited from class java.lang.Object

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

Field Detail

AIC

public final double AIC

Akaike information criterion

See Also:

Wikipedia: Akaike information criterion

BIC

public final double BIC

Bayesian information criterion

See Also:

Wikipedia: Bayesian information criterion