|
||||||||||
PREV CLASS NEXT CLASS | FRAMES NO FRAMES | |||||||||
SUMMARY: NESTED | FIELD | CONSTR | METHOD | DETAIL: FIELD | CONSTR | METHOD |
java.lang.Objectorg.apache.commons.math3.stat.regression.AbstractMultipleLinearRegression
org.apache.commons.math3.stat.regression.GLSMultipleLinearRegression
public class GLSMultipleLinearRegression
The GLS implementation of the multiple linear regression. GLS assumes a general covariance matrix Omega of the error
u ~ N(0, Omega)Estimated by GLS,
b=(X' Omega^-1 X)^-1X'Omega^-1 ywhose variance is
Var(b)=(X' Omega^-1 X)^-1
Constructor Summary | |
---|---|
GLSMultipleLinearRegression()
|
Method Summary | |
---|---|
protected RealVector |
calculateBeta()
Calculates beta by GLS. |
protected RealMatrix |
calculateBetaVariance()
Calculates the variance on the beta. |
protected double |
calculateErrorVariance()
Calculates the estimated variance of the error term using the formula |
protected RealMatrix |
getOmegaInverse()
Get the inverse of the covariance. |
protected void |
newCovarianceData(double[][] omega)
Add the covariance data. |
void |
newSampleData(double[] y,
double[][] x,
double[][] covariance)
Replace sample data, overriding any previous sample. |
Methods inherited from class org.apache.commons.math3.stat.regression.AbstractMultipleLinearRegression |
---|
calculateResiduals, calculateYVariance, estimateErrorVariance, estimateRegressandVariance, estimateRegressionParameters, estimateRegressionParametersStandardErrors, estimateRegressionParametersVariance, estimateRegressionStandardError, estimateResiduals, getX, getY, isNoIntercept, newSampleData, newXSampleData, newYSampleData, setNoIntercept, validateCovarianceData, validateSampleData |
Methods inherited from class java.lang.Object |
---|
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait |
Constructor Detail |
---|
public GLSMultipleLinearRegression()
Method Detail |
---|
public void newSampleData(double[] y, double[][] x, double[][] covariance)
y
- y values of the samplex
- x values of the samplecovariance
- array representing the covariance matrixprotected void newCovarianceData(double[][] omega)
omega
- the [n,n] array representing the covarianceprotected RealMatrix getOmegaInverse()
The inverse of the covariance matrix is lazily evaluated and cached.
protected RealVector calculateBeta()
b=(X' Omega^-1 X)^-1X'Omega^-1 y
calculateBeta
in class AbstractMultipleLinearRegression
protected RealMatrix calculateBetaVariance()
Var(b)=(X' Omega^-1 X)^-1
calculateBetaVariance
in class AbstractMultipleLinearRegression
protected double calculateErrorVariance()
Var(u) = Tr(u' Omega^-1 u)/(n-k)where n and k are the row and column dimensions of the design matrix X.
calculateErrorVariance
in class AbstractMultipleLinearRegression
|
||||||||||
PREV CLASS NEXT CLASS | FRAMES NO FRAMES | |||||||||
SUMMARY: NESTED | FIELD | CONSTR | METHOD | DETAIL: FIELD | CONSTR | METHOD |