Package org.hipparchus.stat.regression

Interface MultipleLinearRegression

All Known Implementing Classes:
AbstractMultipleLinearRegression, GLSMultipleLinearRegression, OLSMultipleLinearRegression
public interface MultipleLinearRegression
The multiple linear regression can be represented in matrix-notation. 
  y=X*b+u
where y is an n-vector regressand, X is a [n,k] matrix whose k columns are called regressors, b is k-vector of regression parameters and u is an n-vector of error terms or residuals. The notation is quite standard in literature, cf eg Davidson and MacKinnon, Econometrics Theory and Methods, 2004.

  • Method Details

    • estimateRegressionParameters

      double[] estimateRegressionParameters()
      Estimates the regression parameters b.
      Returns:
      The [k,1] array representing b

    • estimateRegressionParametersVariance

      double[][] estimateRegressionParametersVariance()
      Estimates the variance of the regression parameters, ie Var(b).
      Returns:
      The [k,k] array representing the variance of b

    • estimateResiduals

      double[] estimateResiduals()
      Estimates the residuals, ie u = y - X*b.
      Returns:
      The [n,1] array representing the residuals

    • estimateRegressandVariance

      double estimateRegressandVariance()
      Returns the variance of the regressand, ie Var(y).
      Returns:
      The double representing the variance of y

    • estimateRegressionParametersStandardErrors

      double[] estimateRegressionParametersStandardErrors()
      Returns the standard errors of the regression parameters.
      Returns:
      standard errors of estimated regression parameters