Examples of OLSMultipleLinearRegression

org.apache.commons.math3.stat.regression.OLSMultipleLinearRegression

Implements ordinary least squares (OLS) to estimate the parameters of a multiple linear regression model.

The regression coefficients, b, satisfy the normal equations:

 X^T X b = X^T y

To solve the normal equations, this implementation uses QR decomposition of the X matrix. (See {@link QRDecomposition} for details on thedecomposition algorithm.) The X matrix, also known as the design matrix, has rows corresponding to sample observations and columns corresponding to independent variables. When the model is estimated using an intercept term (i.e. when {@link #isNoIntercept() isNoIntercept} is false as it is by default), the Xmatrix includes an initial column identically equal to 1. We solve the normal equations as follows:

 X^TX b = X^T y (QR)^T (QR) b = (QR)^Ty R^T (Q^TQ) R b = R^T Q^T y R^T R b = R^T Q^T y (R^T)^-1 R^T R b = (R^T)^-1 R^T Q^T y R b = Q^T y

Given Q and R, the last equation is solved by back-substitution.

@since 2.0


public class OLSAlgorithm
  extends LJavaAlgorithm<EmptyParams, TrainingData, Double[], Double[], Double> {


  public Double[] train(TrainingData data) {
    OLSMultipleLinearRegression r = new OLSMultipleLinearRegression();
    // Convert Double[][] to double[][]
    double[][] x = new double[data.r][data.c];
    double[] y = new double[data.r];


    for (int i=0; i<data.r; i++) {
      for (int j=0; j<data.c; j++) {
        x[i][j] = data.x[i][j].doubleValue();
      }
      y[i] = data.y[i].doubleValue();
    }


    r.newSampleData(y, x);
    // Fixme. Add intercept
    double[] p = r.estimateRegressionParameters();
    Double[] pp = new Double[data.c];
    for (int j=0; j<data.c; j++) {
      pp[j] = p[j];
    }
    System.out.println("Regression Algo: " + Arrays.toString(pp));

All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.

Examples of OLSMultipleLinearRegression

Examples of org.apache.commons.math3.stat.regression.OLSMultipleLinearRegression