|
#include <BandwidthGCVPseudoLogli1D.hh>
|
| BandwidthGCVPseudoLogli1D (double regularizationPower=0.5) |
|
unsigned long | getNonZeroCount () const |
|
unsigned long | getRenormCount () const |
|
virtual double | operator() (const HistoND< Numeric > &histo, const Num2 *densityEstimate, const Num2 *leaveOneOutEstimate, unsigned lenEstimate, const AbsPolyFilter1D &filterUsed) const |
|
virtual double | operator() (const HistoND< Numeric > &histo, double effectiveSampleSize, const Num2 *densityEstimate, const Num2 *leaveOneOutEstimate, unsigned lenEstimate, const AbsPolyFilter1D &filterUsed) const |
|
template<typename Numeric, typename Num2>
class npstat::BandwidthGCVPseudoLogli1D< Numeric, Num2 >
Class for calculating KDE or LOrPE cross-validation pseudo log-likelihood, for 1-dimensional density estimates. This class is intended for use inside degree and/or bandwidth scans.
◆ BandwidthGCVPseudoLogli1D()
template<typename Numeric , typename Num2 >
Parameter "regularizationPower" is used to limit the contributions into the overall pseudo log likelihood from points for which the "leaving one out" density is very low. For those points, instead of "leaving one out" density, we will use the density generated by that point itself divided by pow(N, regularizationPower). This method limits the effect of tails on bandwidth determination.
◆ operator()() [1/2]
template<typename Numeric , typename Num2 >
It should be assumed that the "nFillsInRange" method of the argument histogram returns the actual number of fills (that is, the histogram represents an actual collection of points, has possible bin values of 0, 1, 2, ..., and it is not scaled).
Implements npstat::AbsBandwidthGCV1D< Numeric, Num2 >.
◆ operator()() [2/2]
template<typename Numeric , typename Num2 >
The documentation for this class was generated from the following file:
|