예제 #1
0
  /**
   * Calculates the sample likelihood and BIC score for i given its parents in a simple SEM model.
   */
  private double localSemScore(int i, int[] parents) {
    try {
      ICovarianceMatrix cov = getCovMatrix();
      double varianceY = cov.getValue(i, i);
      double residualVariance = varianceY;
      int n = sampleSize();
      int p = parents.length;
      int k = (p * (p + 1)) / 2 + p;
      //            int k = (p + 1) * (p + 1);
      //            int k = p + 1;
      TetradMatrix covxx = cov.getSelection(parents, parents);
      TetradMatrix covxxInv = covxx.inverse();
      TetradVector covxy = cov.getSelection(parents, new int[] {i}).getColumn(0);
      TetradVector b = covxxInv.times(covxy);
      residualVariance -= covxy.dotProduct(b);

      if (residualVariance <= 0 && verbose) {
        out.println(
            "Nonpositive residual varianceY: resVar / varianceY = "
                + (residualVariance / varianceY));
        return Double.NaN;
      }

      double c = getPenaltyDiscount();

      //            return -n * log(residualVariance) - 2 * k; //AIC
      return -n * Math.log(residualVariance) - c * k * Math.log(n);
      //            return -n * log(residualVariance) - c * k * (log(n) - log(2 * PI));
    } catch (Exception e) {
      e.printStackTrace();
      throw new RuntimeException(e);
      //            throwMinimalLinearDependentSet(parents, cov);
    }
  }
예제 #2
0
  /**
   * @param sampleSize The sample size of the desired data set.
   * @param latentDataSaved True if latent variables should be included in the data set.
   * @return This returns a standardized data set simulated from the model, using the reduced form
   *     method.
   */
  public DataSet simulateDataReducedForm(int sampleSize, boolean latentDataSaved) {
    int numVars = getVariableNodes().size();

    // Calculate inv(I - edgeCoef)
    TetradMatrix edgeCoef = edgeCoef().copy().transpose();

    //        TetradMatrix iMinusB = TetradAlgebra.identity(edgeCoef.rows());
    //        iMinusB.assign(edgeCoef, Functions.minus);

    TetradMatrix iMinusB = TetradAlgebra.identity(edgeCoef.rows()).minus(edgeCoef);

    TetradMatrix inv = iMinusB.inverse();

    // Pick error values e, for each calculate inv * e.
    TetradMatrix sim = new TetradMatrix(sampleSize, numVars);

    // Generate error data with the right variances and covariances, then override this
    // with error data for varaibles that have special distributions defined. Not ideal,
    // but not sure what else to do at the moment. It's better than not taking covariances
    // into account!
    TetradMatrix cholesky = MatrixUtils.choleskyC(errCovar(errorVariances()));

    for (int i = 0; i < sampleSize; i++) {
      TetradVector e = new TetradVector(exogenousData(cholesky, RandomUtil.getInstance()));
      TetradVector ePrime = inv.times(e);
      sim.assignRow(i, ePrime); // sim.viewRow(i).assign(ePrime);
    }

    DataSet fullDataSet = ColtDataSet.makeContinuousData(getVariableNodes(), sim);

    if (latentDataSaved) {
      return fullDataSet;
    } else {
      return DataUtils.restrictToMeasured(fullDataSet);
    }
  }