de.lmu.ifi.dbs.elki.math.statistics.intrinsicdimensionality

Class PWMEstimator

java.lang.Object

de.lmu.ifi.dbs.elki.math.statistics.intrinsicdimensionality.AbstractIntrinsicDimensionalityEstimator

de.lmu.ifi.dbs.elki.math.statistics.intrinsicdimensionality.PWMEstimator

All Implemented Interfaces:

IntrinsicDimensionalityEstimator

public class PWMEstimator
extends AbstractIntrinsicDimensionalityEstimator

Probability weighted moments based estimator. We use the unbiased weights of Maciunas Landwehr et al.:

J. Maciunas Landwehr and N. C. Matalas and J. R. Wallis
Probability weighted moments compared with some traditional techniques in estimating Gumbel parameters and quantiles.
Water Resources Research 15.5 (1979): 1055-1064.

but we pretend we had one additional data point at 0, to not lose valuable data. When implemented exactly, we would have to assign a weight of 0 to the first point. But since we are not using the mean, we don't want to do this. This hack causes this estimator to have a bias to underestimate the ID.

Author:

Jonathan von Brünken, Erich Schubert

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	PWMEstimator.Parameterizer Parameterization class.

Field Summary

Fields

Modifier and Type	Field and Description
static PWMEstimator	STATIC Static instance.

Constructor Summary

Constructors

Constructor and Description
PWMEstimator()

Method Summary

Methods

Modifier and Type	Method and Description
<A> double	estimate(A data, NumberArrayAdapter<?,A> adapter, int len) Estimate from a distance list.

Methods inherited from class de.lmu.ifi.dbs.elki.math.statistics.intrinsicdimensionality.AbstractIntrinsicDimensionalityEstimator

estimate, estimate, estimate

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Field Detail

STATIC

public static final PWMEstimator STATIC

Static instance.

Constructor Detail

PWMEstimator

public PWMEstimator()

Method Detail

estimate

public <A> double estimate(A data,
                  NumberArrayAdapter<?,A> adapter,
                  int len)

Description copied from interface: IntrinsicDimensionalityEstimator

Estimate from a distance list.

Type Parameters:

A - array type

Parameters:

data - Data

adapter - Array adapter

len - Length

Returns:

Estimated intrinsic dimensionality