net.sourceforge.openforecast
Class EvaluationCriteria

java.lang.Object
  net.sourceforge.openforecast.EvaluationCriteria

public class EvaluationCriteria
extends Object

A class of constants defining the various "evaluation criteria" that can be used to compare the accuracy of two forecasting models.

Since:

0.5

Field Summary

static EvaluationCriteria	AIC EvaluationCriteria referring to the Akaike Information Criteria measure.
static EvaluationCriteria	BIAS EvaluationCriteria referring to Bias.
static EvaluationCriteria	BLEND EvaluationCriteria referring to a reasonable blend of all other evaluation criteria.
static EvaluationCriteria	MAD EvaluationCriteria referring to the Mean Absolute Deviation.
static EvaluationCriteria	MAPE EvaluationCriteria referring to the Mean Absolute Percentage Error.
static EvaluationCriteria	MSE EvaluationCriteria referring to the Mean Squared Error.
static EvaluationCriteria	SAE EvaluationCriteria referring to the Sum of the Absolute Error.

Method Summary

boolean	equals(Object obj) Compares two EvaluationCriteria objects for equality.
String	toString() Returns a textual description of this evaluation criteria object.

Methods inherited from class java.lang.Object

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

Field Detail

AIC

public static final EvaluationCriteria AIC

EvaluationCriteria referring to the Akaike Information Criteria measure.

BIAS

public static final EvaluationCriteria BIAS

EvaluationCriteria referring to Bias.

MAD

public static final EvaluationCriteria MAD

EvaluationCriteria referring to the Mean Absolute Deviation.

MAPE

public static final EvaluationCriteria MAPE

EvaluationCriteria referring to the Mean Absolute Percentage Error.

MSE

public static final EvaluationCriteria MSE

EvaluationCriteria referring to the Mean Squared Error.

SAE

public static final EvaluationCriteria SAE

EvaluationCriteria referring to the Sum of the Absolute Error.

BLEND

public static final EvaluationCriteria BLEND

EvaluationCriteria referring to a reasonable blend of all other evaluation criteria. Rather than rely solely on one specific evaluation criteria to pick a "good" model, assess them all and select the model generally regarded as "better" by the majority of the criteria.

Method Detail

equals

public boolean equals(Object obj)

Compares two EvaluationCriteria objects for equality.

Overrides:

equals in class Object

Returns:

true if the given Object is an EvaluationCriteria equivalent to this EvaluationCriteria; otherwise returns false.

toString

public String toString()

Returns a textual description of this evaluation criteria object.

Overrides:

toString in class Object

Returns:

a string representation of the object.