How is bandwidth determined in the Weka KernelEstimator class?

Question

I use Weka to calculate the probability for a given dataset. More specifically, I use the KernelEstimator class .

For good density estimation results, the choice of the bandwidth parameter is crucial, but I have not been able to figure out how the bandwidth parameter is calculated. Used kernel function is a simple Gaussian kernel . Does anyone know how the bandwidth parameter is calculated?

Answer 1

You can find it here :

There you will find

m_SumOfWeights += weight;
double range = m_Values[m_NumValues - 1] - m_Values[0];
if (range > 0) {
  m_StandardDev = Math.max(range / Math.sqrt(m_SumOfWeights), 
      // allow at most 3 sds within one interval
      m_Precision / (2 * 3));
}

m_StandardDev - , "" , .. .