jhpro.stat

Class ConfidenceLevel

java.lang.Object

jhpro.stat.ConfidenceLevel

public class ConfidenceLevel
extends java.lang.Object

Confidence level calculations.

For discoveries, 1-CLb indicates the probability that the background fluctuates to produce a distribution of candidates at least as signal-like as those observed in the data. For discovery, 1-CLb is required to be no more than 2.87x10-7, or twice that, depending on how one interprets what is meant by “five sigma,” including just one side of a Gaussian tail or both. A “three sigma” excess is defined to be 1-CLb = 1.3x10-3 or twice that. But forming discovery p-values, we must compute 1-CLb values of the order of 10-7. This computation involves generating of the order of 10^8 pseudoexperiments, just to be on the safe side.

Read Reference: HEP-EX/9902006. see: Tom Junk,NIM A434, p. 435-443,

Constructor Summary

Constructors

Constructor and Description
ConfidenceLevel() Default constructor.
ConfidenceLevel(int mc) Construct ConfLevel
ConfidenceLevel(int mc, boolean onesided) Build confidence level.

Method Summary

Modifier and Type	Method and Description
void	doc() Show online documentation.
double	get3sProbability() Get 3s probability.
double	get5sProbability() Get 5s probability.
double	getAverageCLs() Get average CLs.
double	getAverageCLsb() Get average CLsb.
double	getCLb() Get the Confidence Level for the background only.
double	getCLb(boolean use_sMC) Get the Confidence Level for the background only.
double	getCLs() Get the Confidence Level defined by CLs = CLsb/CLb.
double	getCLs(boolean use_sMC) Get the Confidence Level defined by CLs = CLsb/CLb.
double	getCLsb() Get the Confidence Level for the signal plus background hypothesis The confidence level for excluding the possibility of simultaneous presence of new particle production and background (the s + b hypothesis)
double	getCLsb(boolean use_sMC) Get the Confidence Level for the signal plus background hypothesis
double	getExpectedCLb_b() Get the expected Confidence Level for the background only if there is only background.These are indications of how well an experiment would do on average in excluding a signal if the signal truly is not present, and are the important figures of merit when optimizing an analysis for exclusion.
double	getExpectedCLb_b(int sigma) Get the expected Confidence Level for the background only if there is only background.
double	getExpectedCLb_sb() Get the expected Confidence Level for the background only if there is signal and background.
double	getExpectedCLb_sb(int sigma) Get the expected Confidence Level for the background only if there is signal and background.
double	getExpectedCLs_b() Get getExpectedCLsb_b/getExpectedCLb_b.
double	getExpectedCLs_b(int sigma) Get getExpectedCLsb_b/getExpectedCLb_b
double	getExpectedCLsb_b() Get the expected Confidence Level for the signal plus background hypothesis if there is only background.
double	getExpectedCLsb_b(int sigma) Get the expected Confidence Level for the signal plus background hypothesis if there is only background.
double	getExpectedStatistic_b()
double	getExpectedStatistic_b(int sigma) Get the expected statistic value in the background only hypothesis
double	getExpectedStatistic_sb(int sigma) Get the expected statistic value in the signal plus background hypothesis
H1D	getLNQb(int bins, double min, double max) Get a histogram of a canonical -2lnQ plot for background hypothesis (full)
H1D	getLNQsb(int bins, double min, double max) Get a histogram of a canonical -2lnQ plot for for signal and background hypothesis
java.util.ArrayList<H1D>	getResults(java.lang.String Option) Display sort of a "canonical" -2lnQ plot.
double	getStatistic()
void	setBtot(double in)
void	setDtot(int in)
void	setLRB(double[] in)
void	setLRS(double[] in)
void	setStot(double in)
void	setTSB(double[] in)
void	setTSD(double in)
void	setTSS(double[] in)

Methods inherited from class java.lang.Object

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

Constructor Detail

ConfidenceLevel

public ConfidenceLevel()

Default constructor.

ConfidenceLevel

public ConfidenceLevel(int mc)

Construct ConfLevel

Parameters:

mc - number of MonteCarlo experiments

ConfidenceLevel

public ConfidenceLevel(int mc,
                       boolean onesided)

Build confidence level.

Parameters:

mc - is the number of Monte Carlo experiments

onesided - specifies if the intervals are one-sided or not.

Method Detail

getExpectedStatistic_b

public double getExpectedStatistic_b(int sigma)

Get the expected statistic value in the background only hypothesis

Parameters:

sigma - between -2 and 2

Returns:

getExpectedStatistic_sb

public double getExpectedStatistic_sb(int sigma)

Get the expected statistic value in the signal plus background hypothesis

Parameters:

sigma -

Returns:

getCLb

public double getCLb()

Get the Confidence Level for the background only. This confidence level quantifies the confidence of a potential discovery, as it expresses the probability that background processes would give fewer than or equal to the number of candidates observed. 1-CLb is the probability that the null hypothesis will give an outcome that looks at least as signal-like as the one observed. For discovery, 1-CLb is required to be no more than 2.87x10-7, or twice that, depending on how one interprets what is meant by “five sigma,” including just one side of a Gaussian tail or both. A “three sigma” excess is defined to be 1-CLb=1.3x10-3 or twice that. But forming discovery p-values, we must compute 1-CLb values of the order of 10-7. This computation involves generating of the order of 10^8 pseudoexperiments, just to be on the safe side.

Returns:

Confidence Level for the background only.

getCLb

public double getCLb(boolean use_sMC)

Get the Confidence Level for the background only. This confidence level quantifies the confidence of a potential discovery, as it expresses the probability that background processes would give fewer than or equal to the number of candidates observed. 1-CLb is the probability that the null hypothesis will give an outcome that looks at least as signal-like as the one observed. For discovery, 1-CLb is required to be no more than 2.87*10-7, or twice that, depending on how one interprets what is meant by “five sigma,” including just one side of a Gaussian tail or both. A “three sigma” excess is defined to be 1-CLb = 1.3*10^-3 or twice that.

But forming discovery p-values, we must compute 1-CLb values of the order of 10-7. This computation involves generating of the order of 10^8 pseudoexperiments, just to be on the safe side.

Parameters:

use_sMC -

Returns:

Confidence Level for the background only.

getCLsb

public double getCLsb()

Get the Confidence Level for the signal plus background hypothesis The confidence level for excluding the possibility of simultaneous presence of new particle production and background (the s + b hypothesis)

Returns:

getCLsb

public double getCLsb(boolean use_sMC)

Get the Confidence Level for the signal plus background hypothesis

Parameters:

use_sMC -

Returns:

getCLs

public double getCLs()

Get the Confidence Level defined by CLs = CLsb/CLb. This quantity is stable w.r.t. background fluctuations.

This hypothesis is excluded at the 95% CL if CLs = 0.05, and at more than the 95% CL if CLs < 0.05, assuming that signal is present.

Returns:

getCLs

public double getCLs(boolean use_sMC)

Get the Confidence Level defined by CLs = CLsb/CLb. This quantity is stable w.r.t. background fluctuations.

This hypothesis is excluded at the 95% CL if CLs = 0.05, and at more than the 95% CL if CLs < 0.05, assuming that signal is present.

Parameters:

use_sMC - use or not MC.

Returns:

getExpectedCLsb_b

public double getExpectedCLsb_b(int sigma)

Get the expected Confidence Level for the signal plus background hypothesis if there is only background.

Parameters:

sigma -

Returns:

getExpectedCLb_sb

public double getExpectedCLb_sb(int sigma)

Get the expected Confidence Level for the background only if there is signal and background.

Parameters:

sigma -

Returns:

getExpectedCLb_b

public double getExpectedCLb_b(int sigma)

Get the expected Confidence Level for the background only if there is only background.

Parameters:

sigma -

Returns:

getAverageCLsb

public double getAverageCLsb()

Get average CLsb.

Returns:

getAverageCLs

public double getAverageCLs()

Get average CLs.

get3sProbability

public double get3sProbability()

Get 3s probability.

get5sProbability

public double get5sProbability()

Get 5s probability.

getResults

public java.util.ArrayList<H1D> getResults(java.lang.String Option)

Display sort of a "canonical" -2lnQ plot. This results in a plot with 2 elements: // - The histogram of -2lnQ for background hypothesis (full) - The histogram of -2lnQ for signal and background hypothesis (dashed) The 2 histograms are respectively named b_hist and sb_hist.

Parameters:

Option -

Returns:

setTSD

public void setTSD(double in)

setLRS

public void setLRS(double[] in)

setLRB

public void setLRB(double[] in)

setBtot

public void setBtot(double in)

setStot

public void setStot(double in)

setDtot

public void setDtot(int in)

getStatistic

public double getStatistic()

setTSB

public void setTSB(double[] in)

setTSS

public void setTSS(double[] in)

getExpectedStatistic_b

public double getExpectedStatistic_b()

getExpectedCLb_sb

public double getExpectedCLb_sb()

Get the expected Confidence Level for the background only if there is signal and background.

Returns:

getExpectedCLs_b

public double getExpectedCLs_b(int sigma)

Get getExpectedCLsb_b/getExpectedCLb_b

Parameters:

sigma -

Returns:

getExpectedCLs_b

public double getExpectedCLs_b()

Get getExpectedCLsb_b/getExpectedCLb_b. These are indications of how well an experiment would do on average in excluding a signal if the signal truly is not present, and are the important figures of merit when optimizing an analysis for exclusion.

Parameters:

sigma -

Returns:

getExpectedCLb_b

public double getExpectedCLb_b()

Get the expected Confidence Level for the background only if there is only background.These are indications of how well an experiment would do on average in excluding a signal if the signal truly is not present, and are the important figures of merit when optimizing an analysis for exclusion.

Returns:

getExpectedCLsb_b

public double getExpectedCLsb_b()

Get the expected Confidence Level for the signal plus background hypothesis if there is only background.

Returns:

getLNQb

public H1D getLNQb(int bins,
                   double min,
                   double max)

Get a histogram of a canonical -2lnQ plot for background hypothesis (full)

Parameters:

bins - number of bins

min - min value

max - max value

Returns:

histogram for -2lnQ plot for background

getLNQsb

public H1D getLNQsb(int bins,
                    double min,
                    double max)

Get a histogram of a canonical -2lnQ plot for for signal and background hypothesis

Parameters:

bins - number of bins

min - min value

max - max value

Returns:

histogram for -2lnQ plot for signal and background hypothesis

doc

public void doc()

Show online documentation.