gov.sandia.cognition.statistics.distribution

Class UnivariateGaussian.CDF.Inverse

java.lang.Object

gov.sandia.cognition.util.AbstractCloneableSerializable

gov.sandia.cognition.statistics.AbstractDistribution<NumberType>

gov.sandia.cognition.statistics.AbstractClosedFormUnivariateDistribution<java.lang.Double>

gov.sandia.cognition.statistics.AbstractClosedFormSmoothUnivariateDistribution

gov.sandia.cognition.statistics.distribution.UnivariateGaussian

gov.sandia.cognition.statistics.distribution.UnivariateGaussian.CDF.Inverse

All Implemented Interfaces:

Evaluator<java.lang.Double,java.lang.Double>, Vectorizable, ScalarFunction<java.lang.Double>, UnivariateScalarFunction, ClosedFormComputableDistribution<java.lang.Double>, ClosedFormDistribution<java.lang.Double>, ClosedFormUnivariateDistribution<java.lang.Double>, ComputableDistribution<java.lang.Double>, Distribution<java.lang.Double>, DistributionWithMean<java.lang.Double>, EstimableDistribution<java.lang.Double,UnivariateGaussian>, SmoothUnivariateDistribution, UnivariateDistribution<java.lang.Double>, CloneableSerializable, java.io.Serializable, java.lang.Cloneable

Enclosing class:

UnivariateGaussian.CDF

public static class UnivariateGaussian.CDF.Inverse
extends UnivariateGaussian
implements UnivariateScalarFunction

Inverts the CumulativeDistribution function. That is, we find the value of z such that p = Pr( x lessThan z ), where x is drawn from a normalized Gaussian. Uses a closed-form computation.

See Also:

Serialized Form

Nested Class Summary

Nested classes/interfaces inherited from class gov.sandia.cognition.statistics.distribution.UnivariateGaussian

UnivariateGaussian.CDF, UnivariateGaussian.ErrorFunction, UnivariateGaussian.IncrementalEstimator, UnivariateGaussian.MaximumLikelihoodEstimator, UnivariateGaussian.PDF, UnivariateGaussian.SufficientStatistic, UnivariateGaussian.WeightedMaximumLikelihoodEstimator

Field Summary

Fields inherited from class gov.sandia.cognition.statistics.distribution.UnivariateGaussian

BIG_Z, DEFAULT_MEAN, DEFAULT_VARIANCE, mean, PI2, SQRT2, variance

Constructor Summary

Constructors

Constructor and Description
Inverse() Creates a new instance of UnivariateGaussian with zero mean and unit variance
Inverse(double mean, double variance) Creates a new instance of UnivariateGaussian
Inverse(UnivariateGaussian other) Copy constructor

Method Summary

Modifier and Type	Method and Description
double	evaluate(double p) Evaluates the Inverse UnivariateGaussian CDF for the given probability.
java.lang.Double	evaluate(java.lang.Double input) Evaluates the function on the given input and returns the output.
static double	evaluate(double p, double mean, double variance) Evaluates the Inverse UnivariateGaussian CDF for the given probability.
double	evaluateAsDouble(java.lang.Double input) Evaluates the scalar function as a double.

Methods inherited from class gov.sandia.cognition.statistics.distribution.UnivariateGaussian

clone, convertFromVector, convertToVector, convolve, getCDF, getEstimator, getMaxSupport, getMean, getMeanAsDouble, getMinSupport, getProbabilityFunction, getStandardDeviation, getVariance, sampleAsDouble, sampleInto, setMean, setVariance, times, toString

Methods inherited from class gov.sandia.cognition.statistics.AbstractClosedFormSmoothUnivariateDistribution

sampleAsDoubles, sampleInto

Methods inherited from class gov.sandia.cognition.statistics.AbstractDistribution

sample, sample

Methods inherited from class java.lang.Object

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

Methods inherited from interface gov.sandia.cognition.statistics.Distribution

sample, sample, sampleInto

Constructor Detail

Inverse

public Inverse()

Creates a new instance of UnivariateGaussian with zero mean and unit variance

Inverse

public Inverse(double mean,
               double variance)

Creates a new instance of UnivariateGaussian

Parameters:

mean - First central moment (expectation) of the distribution

variance - Second central moment (square of standard deviation) of the distribution

Inverse

public Inverse(UnivariateGaussian other)

Copy constructor

Parameters:

other - UnivariateGaussian to copy

Method Detail

evaluate

public java.lang.Double evaluate(java.lang.Double input)

Description copied from interface: Evaluator

Evaluates the function on the given input and returns the output.

Specified by:

evaluate in interface Evaluator<java.lang.Double,java.lang.Double>

Specified by:

evaluate in interface ScalarFunction<java.lang.Double>

Specified by:

evaluate in interface UnivariateScalarFunction

Parameters:

input - The input to evaluate.

Returns:

The output produced by evaluating the input.

evaluateAsDouble

public double evaluateAsDouble(java.lang.Double input)

Description copied from interface: ScalarFunction

Evaluates the scalar function as a double.

Specified by:

evaluateAsDouble in interface ScalarFunction<java.lang.Double>

Specified by:

evaluateAsDouble in interface UnivariateScalarFunction

Parameters:

input - The input value.

Returns:

The scalar output calculated from the given input.

evaluate

public double evaluate(double p)

Evaluates the Inverse UnivariateGaussian CDF for the given probability. If you are using this method many times in a row, then use the two-argument method by caching the standard deviation.

Specified by:

evaluate in interface UnivariateScalarFunction

Parameters:

p - Value at which to solve for x such that x=CDF(p)

Returns:

Value of x such that x=CDF(p)

evaluate

public static double evaluate(double p,
                              double mean,
                              double variance)

Evaluates the Inverse UnivariateGaussian CDF for the given probability. This is faster than computing the single-argument evaluate() method.

Parameters:

p - Value at which to solve for x such that x=CDF(p)

mean - Mean of the distribution

variance - Variance of the distribution.

Returns:

Value of x such that x=CDF(p)