StepwiseLogisticRegressionAnalysis Class

[SerializableAttribute]
public class StepwiseLogisticRegressionAnalysis : IRegressionAnalysis, 
	IMultivariateAnalysis, IAnalysis, ISupervisedLearning<LogisticRegression, double[], double>

<SerializableAttribute>
Public Class StepwiseLogisticRegressionAnalysis
	Implements IRegressionAnalysis, IMultivariateAnalysis, IAnalysis, ISupervisedLearning(Of LogisticRegression, Double(), Double)

// Suppose we have the following data about some patients.
// The first variable is continuous and represent patient
// age. The second variable is dichotomic and give whether
// they smoke or not (this is completely fictional data).

double[][] inputs =
{
    //            Age  Smoking
    new double[] { 55,    0   },  // 1
    new double[] { 28,    0   },  // 2
    new double[] { 65,    1   },  // 3
    new double[] { 46,    0   },  // 4
    new double[] { 86,    1   },  // 5
    new double[] { 56,    1   },  // 6
    new double[] { 85,    0   },  // 7
    new double[] { 33,    0   },  // 8
    new double[] { 21,    1   },  // 9
    new double[] { 42,    1   },  // 10
    new double[] { 33,    0   },  // 11
    new double[] { 20,    1   },  // 12
    new double[] { 43,    1   },  // 13
    new double[] { 31,    1   },  // 14
    new double[] { 22,    1   },  // 15
    new double[] { 43,    1   },  // 16
    new double[] { 46,    0   },  // 17
    new double[] { 86,    1   },  // 18
    new double[] { 56,    1   },  // 19
    new double[] { 55,    0   },  // 20
};

// Additionally, we also have information about whether
// or not they those patients had lung cancer. The array
// below gives 0 for those who did not, and 1 for those
// who did.

double[] output =
{
    0, 0, 0, 1, 1, 1, 0, 0, 0, 1,
    0, 1, 1, 1, 1, 1, 0, 1, 1, 0
};


// Create a Stepwise Logistic Regression analysis
var regression = new StepwiseLogisticRegressionAnalysis(inputs, output,
    new[] { "Age", "Smoking" }, "Cancer");

regression.Compute(); // compute the analysis.

// The full model will be stored in the complete property:
StepwiseLogisticRegressionModel full = regression.Complete;

// The best model will be stored in the current property:
StepwiseLogisticRegressionModel best = regression.Current;

// Let's check the full model results
DataGridBox.Show(full.Coefficients); 

// We can see only the Smoking variable is statistically significant.
// This is an indication the Age variable could be discarded from
// the model.

// And check the best inner model result
DataGridBox.Show(best.Coefficients);

// This is the best nested model found. This model only has the 
// Smoking variable, which is still significant. Since no other
// variables can be dropped, this is the best final model.

// The variables used in the current best model are
string[] inputVariableNames = best.Inputs; // Smoking

// The best model likelihood ratio p-value is
ChiSquareTest test = best.ChiSquare; // {0.816990081334823}

// so the model is distinguishable from a null model. We can also
// query the other nested models by checking the Nested property:

DataGridBox.Show(regression.Nested);

// Finally, we can also use the analysis to classify a new patient
double y = regression.Current.Regression.Compute(new double[] { 1 });

// For a smoking person, the answer probability is approximately 83%.