Package edu.cmu.tetrad.data
Class AndersonDarlingTest
java.lang.Object
edu.cmu.tetrad.data.AndersonDarlingTest
Implements the Anderson-Darling test for normality, with P values calculated as in R's ad.test method (in package
nortest).
Note that in the calculation, points x such that log(1 - normal_cdf(x)) is infinite are ignored.
- Version:
- $Id: $Id
- Author:
- josephramsey
-
Constructor Summary
ConstructorsConstructorDescriptionAndersonDarlingTest
(double[] data) Constructs an Anderson-Darling test for the given column of data. -
Method Summary
Modifier and TypeMethodDescriptiondouble
Constructs an Anderson-Darling test for the given column of data.double
Constructs an Anderson-Darling test for the given column of data.double
getP()
Constructs an Anderson-Darling test for the given column of data.
-
Constructor Details
-
AndersonDarlingTest
public AndersonDarlingTest(double[] data) Constructs an Anderson-Darling test for the given column of data.- Parameters:
data
- the column of data to be analyzed.
-
-
Method Details
-
getASquared
public double getASquared()Constructs an Anderson-Darling test for the given column of data.- Returns:
- the A^2 statistic.
-
getASquaredStar
public double getASquaredStar()Constructs an Anderson-Darling test for the given column of data.- Returns:
- the A^2* statistic, which is the A^2 statistic adjusted heuristically for sample size.
-
getP
public double getP()Constructs an Anderson-Darling test for the given column of data.- Returns:
- the p value of the A^2* statistic, which is interpolated using exponential functions.
-