Package-level declarations

Implements the acceptance/rejection algorithm for uni-variate distributions. The user must supply a continuous distribution that acts as the proposal distribution and the PDF of the distribution from which random variates will be generated. The two distributions must be domain compatible. The proposal distribution's domain must wholly contain the domain of the PDF from which random variates will be generated. If the target PDF's domain is not within the proposal distribution's domain then all proposed values would be rejected.

Uses the autoregressive to anything algorithm to generate correlated uniform variates. The user supplies the correlation of the underlying AR(1) process. The resulting correlation in the u's may not necessarily meet this correlation, due to the correlation matching problem.

Creates an autoregressive order 1 normal process

Bernoulli(probability of success) random variable

Beta(alpha1, alpha2) random variable, range (0,1)

BinomialRV(probability of success, number of trials)

Allows for the generation of bi-variate lognormal random variables. These parameters are all for the lognormal distribution

Allows for the generation of bi-variate normal random variables Constructs a bi-variate normal with the provided parameters

Generates a bivariate Gaussian copula. (u_1, u_2)

Uses a bivariate Gaussian copula to produce (u_1, u_2) and uses the generated (u_1, u_2) to generate (x_1, x_2) where x_1 is from marginal1 and x_2 is from marginal2. The joint distribution of (x_1, x_2) will have a correlation structure implied by the underlying bivariate Gaussian copula.

Chi-Squared(degrees of freedom) random variable

Allows a constant value to pretend to be a random variable

Discrete Empirical Random Variable. Randomly selects from the supplied values in the value array according to the supplied CDF array. The CDF array must have valid probability elements and last element equal to 1. Every element must be greater than or equal to the previous element in the CDF array. That is, monotonically increasing.

Discrete uniform(min, max) random variable

A random variable that samples from the provided data. Each value is equally likely to occur.

Exponential(mean) random variable

GammaRV(shape, scale) random variable

GeneralizeBetaRV(alpha1, alpha2, min, max) random variable

A SAM for specifying the function generate() of random variables

Geometric(probability of success) random variable, range 0, 1, 2, etc.

An interface for getting random variables

Two exponential random variables mixed to get a hyper-exponential. For higher order hyper-exponential use MixtureRV. The mixing probability is the probability of getting the first exponential distribution with mean1

Facilitates the creation of random variables from distributions that implement InverseCDFIfc

JohnsonB(alpha1, alpha2, min, max) random variable

The purpose of this class is to facilitate random variate generation from various distributions without having to create object instances.

LaplaceRV(mean, scale)

Logistic(location, scale) random variable

LogLogistic(shape, scale) random variable

Lognormal(mean, variance). The mean and variance are for the lognormal random variables

Generations d-dimensional Gaussian copula, where the supplied correlation matrix is the correlation for the underlying multi-variate normal

Represents a multi-variate distribution with the specified marginals The sampling of each marginal random variable is independent. That is the resulting distribution has independent marginals. The supplied marginals may be the same distribution or not. If they are all the same, then use MVIndependentRV instead. All the random variables will share the same stream. The sampling ensures that is the sampling is consecutive within the stream and thus independent.

Represents a multi-variate distribution with the specified dimensions. The sampling of each dimension is independent. That is the resulting distribution has independent marginals that are represented by the same distribution as provided by the supplied random variable

Generations multi-dimensional normal random variates

An interface for defining multi-variate random variables

An interface for getting multi-variable samples, each sample has many values held in an array. Clients need to implement the sample(array) function in order to fill up the array with the sample values. The array of size dimension represent 1 sample with elements as the sample values for each coordinate of the dimension. For example, for 2-D, sample returns an array {x0, x1} where x0 is the sample for the first coordinate and x1 is the sample value for the second coordinate.

NegativeBinomial(probability of success, number of trials until rth success)

Normal(mean, variance)

Pearson Type 5(shape, scale) random variable

Pearson Type 6(alpha1, alpha2, beta) random variable

Poisson(mean) random variable

Provides a framework for generating random variates using the ratio of uniforms method. Specifies the pair (u, v), with ratio v/u

An abstract base class for building random variables. Implement the random generation procedure in the method generate().

An interface for defining random variables. The methods sample() and getValue() gets a new value of the random variable sampled accordingly. The method getPreviousValue() returns the value from the last call to sample() or getValue(). The value returned by getPreviousValue() stays the same until the next call to sample() or getValue(). The methods sample() or getValue() always get the next random value. If sample() or getValue() is never called then getPreviousValue() returns Double.NaN. Use sample() or getValue() to get a new random value and use getPreviousValue() to get the last sampled value.

The set of pre-defined types of random variables

Shifted Geometric(probability of success) random variable, range 1, 2, 3, etc.

Shifts the generated value of the supplied random variable by the shift amount. The shift amount must be positive.

Constructs a StudentT distribution dof degrees of freedom

Triangular(min, mode, max) random variable

Constructs a truncated random variable based on the provided distribution

Generates a continuous uniform over the range

Weibull(shape, scale) random variable