Class QuantileDataAnalyzer

java.lang.Object

dataAnalysis.DynamicDataAnalyzerImpl

dataAnalysis.QuantileDataAnalyzer

All Implemented Interfaces:

DynamicDataAnalyzer

public class QuantileDataAnalyzer
extends DynamicDataAnalyzerImpl

Analyzes the data in order to calculate the requested quantiles.

Author:

Federico Granata Date: 24-lug-2003 Time: 12.04.49

Field Summary

Fields inherited from class DynamicDataAnalyzerImpl

alfa, batchLen, batchMean, C1, C2, confInt, deleted, delta, discarded, end, eurDisc, extMean, extVar, heuristic, initData, initial, initialized, initWeight, K, maxData, nSamples, numBatch, parameters, polyOrder, precision, success, sumLastBatch, weightBatchMean

Constructor Summary

Constructors

Constructor	Description
QuantileDataAnalyzer(double alfa, double precision, int maxData, double[] quantile)	Creates a QuantileDataAnalyzer.
QuantileDataAnalyzer(double alfa, double precision, int maxData, double[] quantile, SortAlgorithm sorter)	Creates a QuantileDataAnalyzer.

Method Summary

Modifier and Type	Method	Description
boolean	addSample(double newSample, double weight)	Adds the new sample to the statistic.
protected void	calcVar()	updates the variance
double	getProbability(double quantile)	returns the probability that a number extracted from the empirical distribution analyzed is greater than the quantile.
double	getQuantile(double prob)	returns the quantile with the requested probability.
double[]	getQuantiles()	gets all requested quantiles.
protected boolean	HWtest()	Applies the spectral test to generate the Confidence Intervals.
protected double	search(double element)
protected void	sort()

Methods inherited from class DynamicDataAnalyzerImpl

calcConfInterval, calcConstants, calcEstimatorVar, calcVar, deleteTransient, estimatedMean, getAlfa, getConfInt, getData, getDiscarded, getLastIntervalAvg, getMaxData, getMean, getNullMeasure_upperLimit, getPrecision, getSamples, getSuccess, getVar, heuristicR5, isZero, nullTest, schrubenTest, setParameters, stopMeasure, toString

Methods inherited from class Object

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

Constructor Details

QuantileDataAnalyzer

public QuantileDataAnalyzer(double alfa,
 double precision,
 int maxData,
 double[] quantile,
 SortAlgorithm sorter)

Creates a QuantileDataAnalyzer.

Parameters:

alfa - the quantile required for the confidence interval

precision - maximum amplitude of confidence interval (precision = maxamplitude / mean)

maxData - maximum number of data to be analyzed

quantile - Requested quantiles //TODO: correct??

sorter - Sorting algorithm used to manage data

QuantileDataAnalyzer

public QuantileDataAnalyzer(double alfa,
 double precision,
 int maxData,
 double[] quantile)

Creates a QuantileDataAnalyzer. A default sorting algorithm is used to manage data.

Parameters:

alfa - the quantile required for the confidence interval

precision - maximum amplitude of confidence interval (precision = maxamplitude / mean)

maxData - maximum number of data to be analyzed

quantile - Requested quantiles

Method Details

addSample

public boolean addSample(double newSample,
 double weight)

Adds the new sample to the statistic.

Specified by:

addSample in interface DynamicDataAnalyzer

Overrides:

addSample in class DynamicDataAnalyzerImpl

Parameters:

newSample - the new sample

weight - the weight of the newSample, if it is not needed put 1.

Returns:

true if the confidence interval is smaller than required by the user, or the data analyzed are too many

getQuantile

public double getQuantile(double prob)

returns the quantile with the requested probability.

Parameters:

prob - probability of the quantile

Returns:

the estimated quantile

getQuantiles

public double[] getQuantiles()

gets all requested quantiles.

Returns:

vector of quantiles.

getProbability

public double getProbability(double quantile)

returns the probability that a number extracted from the empirical distribution analyzed is greater than the quantile.

Parameters:

quantile - the requested quantile

Returns:

estimated probability

search

protected double search(double element)

sort

protected void sort()

HWtest

protected boolean HWtest()

Applies the spectral test to generate the Confidence Intervals. see: P. Heidelberger, Peter D. Welch "A spectral method for confidence interval generation and run length control in simulations"

Overrides:

HWtest in class DynamicDataAnalyzerImpl

Returns:

true if the precision requirement met. false if not.

calcVar

protected void calcVar()

updates the variance

Overrides:

calcVar in class DynamicDataAnalyzerImpl