internal NestedLogisticCoefficient(StepwiseLogisticRegressionModel analysis, int index)
{
this.analysis = analysis;
this.index = index;
}
/// <summary>
/// Computes one step of the Stepwise Logistic Regression Analysis.
/// </summary>
/// <returns>
/// Returns the index of the variable discarded in the step or -1
/// in case no variable could be discarded.
/// </returns>
///
public int DoStep()
{
ChiSquareTest[] tests = null;
// Check if we are performing the first step
if (currentModel == null)
{
// This is the first step. We should create the full model.
int inputCount = inputData[0].Length;
int[] variables = Vector.Range(0, inputCount);
var regression = new LogisticRegression()
{
NumberOfInputs = inputCount
};
fit(regression, inputData, outputData);
ChiSquareTest test = regression.ChiSquare(inputData, outputData);
fullLikelihood = regression.GetLogLikelihood(inputData, outputData);
if (Double.IsNaN(fullLikelihood))
{
throw new ConvergenceException(
"Perfect separation detected. Please rethink the use of logistic regression.");
}
tests = new ChiSquareTest[regression.NumberOfInputs + 1];
currentModel = new StepwiseLogisticRegressionModel(this, regression, variables, test, tests);
completeModel = currentModel;
}
// Verify first if a variable reduction is possible
if (currentModel.Regression.NumberOfInputs == 1)
{
return(-1); // cannot reduce further
}
// Now go and create the diminished nested models
var nestedModels = new StepwiseLogisticRegressionModel[currentModel.Regression.NumberOfInputs];
for (int i = 0; i < nestedModels.Length; i++)
{
// Create a diminished nested model without the current variable
LogisticRegression regression = new LogisticRegression()
{
NumberOfInputs = currentModel.Regression.NumberOfInputs - 1
};
int[] variables = currentModel.Variables.RemoveAt(i);
double[][] subset = inputData.Get(null, variables);
fit(regression, subset, outputData);
// Check the significance of the nested model
double logLikelihood = regression.GetLogLikelihood(subset, outputData);
double ratio = 2.0 * (fullLikelihood - logLikelihood);
ChiSquareTest test = new ChiSquareTest(ratio, inputNames.Length - variables.Length)
{
Size = threshold
};
if (tests != null)
{
tests[i + 1] = test;
}
// Store the nested model
nestedModels[i] = new StepwiseLogisticRegressionModel(this, regression, variables, test, null);
}
// Select the model with the highest p-value
double pmax = 0;
int imax = -1;
for (int i = 0; i < nestedModels.Length; i++)
{
if (nestedModels[i].ChiSquare.PValue >= pmax)
{
imax = i;
pmax = nestedModels[i].ChiSquare.PValue;
}
}
// Create the read-only nested model collection
this.nestedModelCollection = new StepwiseLogisticRegressionModelCollection(nestedModels);
// If the model with highest p-value is not significant,
if (imax >= 0 && pmax > threshold)
{
// Then this means the variable can be safely discarded from the full model
int removed = currentModel.Variables[imax];
// Our diminished nested model will become our next full model.
this.currentModel = nestedModels[imax];
// Finally, return the index of the removed variable
return(removed);
}
else
{
// Else we can not safely remove any variable from the model.
return(-1);
}
}
