org.hipparchus.stat.interval

Class BinomialProportion

java.lang.Object

org.hipparchus.stat.interval.BinomialProportion

public class BinomialProportion
extends Object

Utility methods to generate confidence intervals for a binomial proportion.

See Also:

Binomial proportion confidence interval (Wikipedia)

Method Summary

Modifier and Type	Method and Description
static ConfidenceInterval	getAgrestiCoullInterval(int numberOfTrials, double probabilityOfSuccess, double confidenceLevel) Create an Agresti-Coull binomial confidence interval for the true probability of success of an unknown binomial distribution with the given observed number of trials, probability of success and confidence level.
static ConfidenceInterval	getClopperPearsonInterval(int numberOfTrials, double probabilityOfSuccess, double confidenceLevel) Create a Clopper-Pearson binomial confidence interval for the true probability of success of an unknown binomial distribution with the given observed number of trials, probability of success and confidence level.
static ConfidenceInterval	getNormalApproximationInterval(int numberOfTrials, double probabilityOfSuccess, double confidenceLevel) Create a binomial confidence interval using normal approximation for the true probability of success of an unknown binomial distribution with the given observed number of trials, probability of success and confidence level.
static ConfidenceInterval	getWilsonScoreInterval(int numberOfTrials, double probabilityOfSuccess, double confidenceLevel) Create an Wilson score binomial confidence interval for the true probability of success of an unknown binomial distribution with the given observed number of trials, probability of success and confidence level.

Methods inherited from class java.lang.Object

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

Method Detail

getAgrestiCoullInterval

public static ConfidenceInterval getAgrestiCoullInterval(int numberOfTrials,
                                                         double probabilityOfSuccess,
                                                         double confidenceLevel)
                                                  throws MathIllegalArgumentException

Create an Agresti-Coull binomial confidence interval for the true probability of success of an unknown binomial distribution with the given observed number of trials, probability of success and confidence level.

Preconditions:

• numberOfTrials must be positive
• probabilityOfSuccess must be between 0 and 1 (inclusive)
• confidenceLevel must be strictly between 0 and 1 (exclusive)

Parameters:

numberOfTrials - number of trials

probabilityOfSuccess - observed probability of success

confidenceLevel - desired probability that the true probability of success falls within the returned interval

Returns:

Confidence interval containing the probability of success with probability confidenceLevel

Throws:

MathIllegalArgumentException - if numberOfTrials <= 0.

MathIllegalArgumentException - if probabilityOfSuccess is not in the interval [0, 1].

MathIllegalArgumentException - if confidenceLevel is not in the interval (0, 1).

See Also:

Agresti-Coull interval (Wikipedia)

getClopperPearsonInterval

public static ConfidenceInterval getClopperPearsonInterval(int numberOfTrials,
                                                           double probabilityOfSuccess,
                                                           double confidenceLevel)
                                                    throws MathIllegalArgumentException

Create a Clopper-Pearson binomial confidence interval for the true probability of success of an unknown binomial distribution with the given observed number of trials, probability of success and confidence level.

Preconditions:

• numberOfTrials must be positive
• probabilityOfSuccess must be between 0 and 1 (inclusive)
• confidenceLevel must be strictly between 0 and 1 (exclusive)

Parameters:

numberOfTrials - number of trials

probabilityOfSuccess - observed probability of success

confidenceLevel - desired probability that the true probability of success falls within the returned interval

Returns:

Confidence interval containing the probability of success with probability confidenceLevel

Throws:

MathIllegalArgumentException - if numberOfTrials <= 0.

MathIllegalArgumentException - if probabilityOfSuccess is not in the interval [0, 1].

MathIllegalArgumentException - if confidenceLevel is not in the interval (0, 1).

See Also:

Clopper-Pearson interval (Wikipedia)

getNormalApproximationInterval

public static ConfidenceInterval getNormalApproximationInterval(int numberOfTrials,
                                                                double probabilityOfSuccess,
                                                                double confidenceLevel)
                                                         throws MathIllegalArgumentException

Create a binomial confidence interval using normal approximation for the true probability of success of an unknown binomial distribution with the given observed number of trials, probability of success and confidence level.

Preconditions:

• numberOfTrials must be positive
• probabilityOfSuccess must be between 0 and 1 (inclusive)
• confidenceLevel must be strictly between 0 and 1 (exclusive)

Parameters:

numberOfTrials - number of trials

probabilityOfSuccess - observed probability of success

confidenceLevel - desired probability that the true probability of success falls within the returned interval

Returns:

Confidence interval containing the probability of success with probability confidenceLevel

Throws:

MathIllegalArgumentException - if numberOfTrials <= 0.

MathIllegalArgumentException - if probabilityOfSuccess is not in the interval [0, 1].

MathIllegalArgumentException - if confidenceLevel is not in the interval (0, 1).

See Also:

Normal approximation interval (Wikipedia)

getWilsonScoreInterval

public static ConfidenceInterval getWilsonScoreInterval(int numberOfTrials,
                                                        double probabilityOfSuccess,
                                                        double confidenceLevel)
                                                 throws MathIllegalArgumentException

Create an Wilson score binomial confidence interval for the true probability of success of an unknown binomial distribution with the given observed number of trials, probability of success and confidence level.

Preconditions:

• numberOfTrials must be positive
• probabilityOfSuccess must be between 0 and 1 (inclusive)
• confidenceLevel must be strictly between 0 and 1 (exclusive)

Parameters:

numberOfTrials - number of trials

probabilityOfSuccess - observed probability of success

confidenceLevel - desired probability that the true probability of success falls within the returned interval

Returns:

Confidence interval containing the probability of success with probability confidenceLevel

Throws:

MathIllegalArgumentException - if numberOfTrials <= 0.

MathIllegalArgumentException - if probabilityOfSuccess is not in the interval [0, 1].

MathIllegalArgumentException - if confidenceLevel is not in the interval (0, 1).

See Also:

Wilson score interval (Wikipedia)