 NAME
 SYNOPSIS
 DESCRIPTION
 Bernoulli
 Beta
 Binomial
 Exponential
 Exponential Power
 Cauchy
 ChiSquared
 Dirichlet
 Erlang
 Fdistribution
 Uniform/Flat distribution
 Gamma
 Gaussian/Normal
 Gaussian Tail
 Landau
 Geometric
 Hypergeometric
 Gumbel
 Logistic
 Lognormal
 Logarithmic
 Multinomial
 Negative Binomial
 Pascal
 Pareto
 Poisson
 Rayleigh
 Studentt
 Laplace
 Levy
 Weibull
 Spherical Vector
 Shuffling and Sampling
 EXAMPLES
 AUTHORS
 COPYRIGHT AND LICENSE
NAME
Math::GSL::Randist  Probability Distributions
SYNOPSIS
use Math::GSL::RNG;
use Math::GSL::Randist qw/:all/;
my $rng = Math::GSL::RNG>new();
my $coinflip = gsl_ran_bernoulli($rng>raw(), .5);
DESCRIPTION
Here is a list of all the functions included in this module. For all sampling methods, the first argument $r is a raw gsl_rnd structure retrieve by calling raw() on an Math::GSL::RNG object.
Bernoulli
 gsl_ran_bernoulli($r, $p)

This function returns either 0 or 1, the result of a Bernoulli trial with probability $p. The probability distribution for a Bernoulli trial is, p(0) = 1  $p and p(1) = $p. $r is a gsl_rng structure.
 gsl_ran_bernoulli_pdf($k, $p)

This function computes the probability p($k) of obtaining $k from a Bernoulli distribution with probability parameter $p, using the formula given above.
Beta
 gsl_ran_beta($r, $a, $b)

This function returns a random variate from the beta distribution. The distribution function is, p($x) dx = {Gamma($a+$b) \ Gamma($a) Gamma($b)} $x**{$a1} (1$x)**{$b1} dx for 0 <= $x <= 1.$r is a gsl_rng structure.
 gsl_ran_beta_pdf($x, $a, $b)

This function computes the probability density p($x) at $x for a beta distribution with parameters $a and $b, using the formula given above.
Binomial
 gsl_ran_binomial($k, $p, $n)

This function returns a random integer from the binomial distribution, the number of successes in n independent trials with probability $p. The probability distribution for binomial variates is p($k) = {$n! \ $k! ($n$k)! } $p**$k (1$p)^{$n$k} for 0 <= $k <= $n. Uses Binomial Triangle Parallelogram Exponential algorithm.
 gsl_ran_binomial_knuth($k, $p, $n)

Alternative and original implementation for gsl_ran_binomial using Knuth's algorithm.
 gsl_ran_binomial_tpe($k, $p, $n)

Same as gsl_ran_binomial.
 gsl_ran_binomial_pdf($k, $p, $n)

This function computes the probability p($k) of obtaining $k from a binomial distribution with parameters $p and $n, using the formula given above.
Exponential
 gsl_ran_exponential($r, $mu)

This function returns a random variate from the exponential distribution with mean $mu. The distribution is, p($x) dx = {1 \ $mu} exp($x/$mu) dx for $x >= 0. $r is a gsl_rng structure.
 gsl_ran_exponential_pdf($x, $mu)

This function computes the probability density p($x) at $x for an exponential distribution with mean $mu, using the formula given above.
Exponential Power
 gsl_ran_exppow($r, $a, $b)

This function returns a random variate from the exponential power distribution with scale parameter $a and exponent $b. The distribution is, p(x) dx = {1 / 2 $a Gamma(1+1/$b)} exp($x/$a**$b) dx for $x >= 0. For $b = 1 this reduces to the Laplace distribution. For $b = 2 it has the same form as a gaussian distribution, but with $a = sqrt(2) sigma. $r is a gsl_rng structure.
 gsl_ran_exppow_pdf($x, $a, $b)

This function computes the probability density p($x) at $x for an exponential power distribution with scale parameter $a and exponent $b, using the formula given above.
Cauchy
 gsl_ran_cauchy($r, $scale)

This function returns a random variate from the Cauchy distribution with $scale. The probability distribution for Cauchy random variates is,
p(x) dx = {1 / $scale pi (1 + (x/$$scale)**2) } dx
for x in the range infinity to +infinity. The Cauchy distribution is also known as the Lorentz distribution. $r is a gsl_rng structure.
 gsl_ran_cauchy_pdf($x, $scale)

This function computes the probability density p($x) at $x for a Cauchy distribution with $scale, using the formula given above.
ChiSquared
 gsl_ran_chisq($r, $nu)

This function returns a random variate from the chisquared distribution with $nu degrees of freedom. The distribution function is, p(x) dx = {1 / 2 Gamma($nu/2) } (x/2)**{$nu/2  1} exp(x/2) dx for $x >= 0. $r is a gsl_rng structure.
 gsl_ran_chisq_pdf($x, $nu)

This function computes the probability density p($x) at $x for a chisquared distribution with $nu degrees of freedom, using the formula given above.
Dirichlet
 gsl_ran_dirichlet($r, $alpha)

This function returns an array of K (where K = length of $alpha array) random variates from a Dirichlet distribution of order K1. The distribution function is
p(\theta_1, ..., \theta_K) d\theta_1 ... d\theta_K = (1/Z) \prod_{i=1}^K \theta_i^{\alpha_i  1} \delta(1 \sum_{i=1}^K \theta_i) d\theta_1 ... d\theta_K
for theta_i >= 0 and alpha_i > 0. The delta function ensures that \sum \theta_i = 1. The normalization factor Z is
Z = {\prod_{i=1}^K \Gamma(\alpha_i)} / {\Gamma( \sum_{i=1}^K \alpha_i)}
The random variates are generated by sampling K values from gamma distributions with parameters a=alpha_i, b=1, and renormalizing. See A.M. Law, W.D. Kelton, Simulation Modeling and Analysis (1991).
 gsl_ran_dirichlet_pdf($theta, $alpha)

This function computes the probability density p(\theta_1, ... , \theta_K) at theta[K] for a Dirichlet distribution with parameters alpha[K], using the formula given above. $alpha and $theta should be array references of the same size. Theta should be normalized to sum to 1.
 gsl_ran_dirichlet_lnpdf($theta, $alpha)

This function computes the logarithm of the probability density p(\theta_1, ... , \theta_K) for a Dirichlet distribution with parameters alpha[K]. $alpha and $theta should be array references of the same size. Theta should be normalized to sum to 1.
Erlang
 gsl_ran_erlang($r, $scale, $shape)

Equivalent to gsl_ran_gamma($r, $shape, $scale) where $shape is an integer.
 gsl_ran_erlang_pdf

Equivalent to gsl_ran_gamma_pdf($r, $shape, $scale) where $shape is an integer.
Fdistribution
 gsl_ran_fdist($r, $nu1, $nu2)

This function returns a random variate from the Fdistribution with degrees of freedom nu1 and nu2. The distribution function is, p(x) dx = { Gamma(($nu_1 + $nu_2)/2) / Gamma($nu_1/2) Gamma($nu_2/2) } $nu_1**{$nu_1/2} $nu_2**{$nu_2/2} x**{$nu_1/2  1} ($nu_2 + $nu_1 x)**{$nu_1/2 $nu_2/2} for $x >= 0. $r is a gsl_rng structure.
 gsl_ran_fdist_pdf($x, $nu1, $nu2)

This function computes the probability density p(x) at x for an Fdistribution with nu1 and nu2 degrees of freedom, using the formula given above.
Uniform/Flat distribution
 gsl_ran_flat($r, $a, $b)

This function returns a random variate from the flat (uniform) distribution from a to b. The distribution is, p(x) dx = {1 / ($b$a)} dx if $a <= x < $b and 0 otherwise. $r is a gsl_rng structure.
 gsl_ran_flat_pdf($x, $a, $b)

This function computes the probability density p($x) at $x for a uniform distribution from $a to $b, using the formula given above.
Gamma
 gsl_ran_gamma($r, $shape, $scale)

This function returns a random variate from the gamma distribution. The distribution function is, p(x) dx = {1 \over \Gamma($shape) $scale^$shape} x^{$shape1} e^{x/$scale} dx for x > 0. Uses MarsagliaTsang method. Can also be called as gsl_ran_gamma_mt.
 gsl_ran_gamma_pdf($x, $shape, $scale)

This function computes the probability density p($x) at $x for a gamma distribution with parameters $shape and $scale, using the formula given above.
 gsl_ran_gamma($r, $shape, $scale)

Same as gsl_ran_gamma.
 gsl_ran_gamma_knuth($r, $shape, $scale)

Alternative implementation for gsl_ran_gamma, using algorithm in Knuth volume 2.
Gaussian/Normal
 gsl_ran_gaussian($r, $sigma)

This function returns a Gaussian random variate, with mean zero and standard deviation $sigma. The probability distribution for Gaussian random variates is, p(x) dx = {1 / sqrt{2 pi $sigma**2}} exp(x**2 / 2 $sigma**2) dx for x in the range infinity to +infinity. $r is a gsl_rng structure. Uses BoxMueller (polar) method.
 gsl_ran_gaussian_ratio_method($r, $sigma)

This function computes a Gaussian random variate using the alternative KindermanMonahanLeva ratio method.
 gsl_ran_gaussian_ziggurat($r, $sigma)

This function computes a Gaussian random variate using the alternative MarsagliaTsang ziggurat ratio method. The Ziggurat algorithm is the fastest available algorithm in most cases. $r is a gsl_rng structure.
 gsl_ran_gaussian_pdf($x, $sigma)

This function computes the probability density p($x) at $x for a Gaussian distribution with standard deviation sigma, using the formula given above.
 gsl_ran_ugaussian($r)
 gsl_ran_ugaussian_ratio_method($r)
 gsl_ran_ugaussian_pdf($x)

This function computes results for the unit Gaussian distribution. It is equivalent to the gaussian functions above with a standard deviation of one, sigma = 1.
 gsl_ran_bivariate_gaussian($r, $sigma_x, $sigma_y, $rho)

This function generates a pair of correlated Gaussian variates, with mean zero, correlation coefficient rho and standard deviations $sigma_x and $sigma_y in the x and y directions. The first value returned is x and the second y. The probability distribution for bivariate Gaussian random variates is, p(x,y) dx dy = {1 / 2 pi $sigma_x $sigma_y sqrt{1$rho**2}} exp ((x**2/$sigma_x**2 + y**2/$sigma_y**2  2 $rho x y/($sigma_x $sigma_y))/2(1 $rho**2)) dx dy for x,y in the range infinity to +infinity. The correlation coefficient $rho should lie between 1 and 1. $r is a gsl_rng structure.
 gsl_ran_bivariate_gaussian_pdf($x, $y, $sigma_x, $sigma_y, $rho)

This function computes the probability density p($x,$y) at ($x,$y) for a bivariate Gaussian distribution with standard deviations $sigma_x, $sigma_y and correlation coefficient $rho, using the formula given above.
Gaussian Tail
 gsl_ran_gaussian_tail($r, $a, $sigma)

This function provides random variates from the upper tail of a Gaussian distribution with standard deviation sigma. The values returned are larger than the lower limit a, which must be positive. The probability distribution for Gaussian tail random variates is, p(x) dx = {1 / N($a; $sigma) sqrt{2 pi sigma**2}} exp( x**2/(2 sigma**2)) dx for x > $a where N($a; $sigma) is the normalization constant, N($a; $sigma) = (1/2) erfc($a / sqrt(2 $sigma**2)). $r is a gsl_rng structure.
 gsl_ran_gaussian_tail_pdf($x, $a, $gaussian)

This function computes the probability density p($x) at $x for a Gaussian tail distribution with standard deviation sigma and lower limit $a, using the formula given above.
 gsl_ran_ugaussian_tail($r, $a)

This functions compute results for the tail of a unit Gaussian distribution. It is equivalent to the functions above with a standard deviation of one, $sigma = 1. $r is a gsl_rng structure.
 gsl_ran_ugaussian_tail_pdf($x, $a)

This functions compute results for the tail of a unit Gaussian distribution. It is equivalent to the functions above with a standard deviation of one, $sigma = 1.
Landau
 gsl_ran_landau($r)

This function returns a random variate from the Landau distribution. The probability distribution for Landau random variates is defined analytically by the complex integral, p(x) = (1/(2 \pi i)) \int_{ci\infty}^{c+i\infty} ds exp(s log(s) + x s) For numerical purposes it is more convenient to use the following equivalent form of the integral, p(x) = (1/\pi) \int_0^\infty dt \exp(t \log(t)  x t) \sin(\pi t). $r is a gsl_rng structure.
 gsl_ran_landau_pdf($x)

This function computes the probability density p($x) at $x for the Landau distribution using an approximation to the formula given above.
Geometric
 gsl_ran_geometric($r, $p)

This function returns a random integer from the geometric distribution, the number of independent trials with probability $p until the first success. The probability distribution for geometric variates is, p(k) = p (1$p)^(k1) for k >= 1. Note that the distribution begins with k=1 with this definition. There is another convention in which the exponent k1 is replaced by k. $r is a gsl_rng structure.
 gsl_ran_geometric_pdf($k, $p)

This function computes the probability p($k) of obtaining $k from a geometric distribution with probability parameter p, using the formula given above.
Hypergeometric
 gsl_ran_hypergeometric($r, $n1, $n2, $t)

This function returns a random integer from the hypergeometric distribution. The probability distribution for hypergeometric random variates is, p(k) = C(n_1, k) C(n_2, t  k) / C(n_1 + n_2, t) where C(a,b) = a!/(b!(ab)!) and t <= n_1 + n_2. The domain of k is max(0,tn_2), ..., min(t,n_1). If a population contains n_1 elements of "type 1" and n_2 elements of "type 2" then the hypergeometric distribution gives the probability of obtaining k elements of "type 1" in t samples from the population without replacement. $r is a gsl_rng structure.
 gsl_ran_hypergeometric_pdf($k, $n1, $n2, $t)

This function computes the probability p(k) of obtaining k from a hypergeometric distribution with parameters $n1, $n2 $t, using the formula given above.
Gumbel
 gsl_ran_gumbel1($r, $a, $b)

This function returns a random variate from the Type1 Gumbel distribution. The Type1 Gumbel distribution function is, p(x) dx = a b \exp((b \exp(ax) + ax)) dx for \infty < x < \infty. $r is a gsl_rng structure.
 gsl_ran_gumbel1_pdf($x, $a, $b)

This function computes the probability density p($x) at $x for a Type1 Gumbel distribution with parameters $a and $b, using the formula given above.
 gsl_ran_gumbel2($r, $a, $b)

This function returns a random variate from the Type2 Gumbel distribution. The Type2 Gumbel distribution function is, p(x) dx = a b x^{a1} \exp(b x^{a}) dx for 0 < x < \infty. $r is a gsl_rng structure.
 gsl_ran_gumbel2_pdf($x, $a, $b)

This function computes the probability density p($x) at $x for a Type2 Gumbel distribution with parameters $a and $b, using the formula given above.
Logistic
 gsl_ran_logistic($r, $a)

This function returns a random variate from the logistic distribution. The distribution function is, p(x) dx = { \exp(x/a) \over a (1 + \exp(x/a))^2 } dx for \infty < x < +\infty. $r is a gsl_rng structure.
 gsl_ran_logistic_pdf($x, $a)

This function computes the probability density p($x) at $x for a logistic distribution with scale parameter $a, using the formula given above.
Lognormal
 gsl_ran_lognormal($r, $zeta, $sigma)

This function returns a random variate from the lognormal distribution. The distribution function is, p(x) dx = {1 \over x \sqrt{2 \pi \sigma^2} } \exp((\ln(x)  \zeta)^2/2 \sigma^2) dx for x > 0. $r is a gsl_rng structure.
 gsl_ran_lognormal_pdf($x, $zeta, $sigma)

This function computes the probability density p($x) at $x for a lognormal distribution with parameters $zeta and $sigma, using the formula given above.
Logarithmic
 gsl_ran_logarithmic($r, $p)

This function returns a random integer from the logarithmic distribution. The probability distribution for logarithmic random variates is, p(k) = {1 \over \log(1p)} {(p^k \over k)} for k >= 1. $r is a gsl_rng structure.
 gsl_ran_logarithmic_pdf($k, $p)

This function computes the probability p($k) of obtaining $k from a logarithmic distribution with probability parameter $p, using the formula given above.
Multinomial
 gsl_ran_multinomial($r, $P, $N)

This function computes and returns a random sample n[] from the multinomial distribution formed by N trials from an underlying distribution p[K]. The distribution function for n[] is,
P(n_1, n_2, ..., n_K) = (N!/(n_1! n_2! ... n_K!)) p_1^n_1 p_2^n_2 ... p_K^n_K
where (n_1, n_2, ..., n_K) are nonnegative integers with sum_{k=1}^K n_k = N, and (p_1, p_2, ..., p_K) is a probability distribution with \sum p_i = 1. If the array p[K] is not normalized then its entries will be treated as weights and normalized appropriately.
Random variates are generated using the conditional binomial method (see C.S. Davis, The computer generation of multinomial random variates, Comp. Stat. Data Anal. 16 (1993) 205217 for details).
 gsl_ran_multinomial_pdf($counts, $P)

This function returns the probability for the multinomial distribution P(counts[1], counts[2], ..., counts[K]) with parameters p[K].
 gsl_ran_multinomial_lnpdf($counts, $P)

This function returns the logarithm of the probability for the multinomial distribution P(counts[1], counts[2], ..., counts[K]) with parameters p[K].
Negative Binomial
 gsl_ran_negative_binomial($r, $p, $n)

This function returns a random integer from the negative binomial distribution, the number of failures occurring before n successes in independent trials with probability p of success. The probability distribution for negative binomial variates is, p(k) = {\Gamma(n + k) \over \Gamma(k+1) \Gamma(n) } p^n (1p)^k Note that n is not required to be an integer.
 gsl_ran_negative_binomial_pdf($k, $p, $n)

This function computes the probability p($k) of obtaining $k from a negative binomial distribution with parameters $p and $n, using the formula given above.
Pascal
 gsl_ran_pascal($r, $p, $n)

This function returns a random integer from the Pascal distribution. The Pascal distribution is simply a negative binomial distribution with an integer value of $n. p($k) = {($n + $k  1)! \ $k! ($n  1)! } $p**$n (1$p)**$k for $k >= 0. $r is gsl_rng structure
 gsl_ran_pascal_pdf($k, $p, $n)

This function computes the probability p($k) of obtaining $k from a Pascal distribution with parameters $p and $n, using the formula given above.
Pareto
 gsl_ran_pareto($r, $a, $b)

This function returns a random variate from the Pareto distribution of order $a. The distribution function is p($x) dx = ($a/$b) / ($x/$b)^{$a+1} dx for $x >= $b. $r is a gsl_rng structure
 gsl_ran_pareto_pdf($x, $a, $b)

This function computes the probability density p(x) at x for a Pareto distribution with exponent a and scale b, using the formula given above.
Poisson
 gsl_ran_poisson($r, $lambda)

This function returns a random integer from the Poisson distribution with mean $lambda. $r is a gsl_rng structure. The probability distribution for Poisson variates is,
p(k) = {$lambda**$k \ $k!} exp($lambda)
for $k >= 0. $r is a gsl_rng structure.
 gsl_ran_poisson_pdf($k, $lambda)

This function computes the probability p($k) of obtaining $k from a Poisson distribution with mean $lambda, using the formula given above.
Rayleigh
 gsl_ran_rayleigh($r, $sigma)

This function returns a random variate from the Rayleigh distribution with scale parameter sigma. The distribution is, p(x) dx = {x \over \sigma^2} \exp( x^2/(2 \sigma^2)) dx for x > 0. $r is a gsl_rng structure
 gsl_ran_rayleigh_pdf($x, $sigma)

This function computes the probability density p($x) at $x for a Rayleigh distribution with scale parameter sigma, using the formula given above.
 gsl_ran_rayleigh_tail($r, $a, $sigma)

This function returns a random variate from the tail of the Rayleigh distribution with scale parameter $sigma and a lower limit of $a. The distribution is, p(x) dx = {x \over \sigma^2} \exp ((a^2  x^2) /(2 \sigma^2)) dx for x > a. $r is a gsl_rng structure
 gsl_ran_rayleigh_tail_pdf($x, $a, $sigma)

This function computes the probability density p($x) at $x for a Rayleigh tail distribution with scale parameter $sigma and lower limit $a, using the formula given above.
Studentt
 gsl_ran_tdist($r, $nu)

This function returns a random variate from the tdistribution. The distribution function is, p(x) dx = {\Gamma((\nu + 1)/2) \over \sqrt{\pi \nu} \Gamma(\nu/2)} (1 + x^2/\nu)^{(\nu + 1)/2} dx for \infty < x < +\infty.
 gsl_ran_tdist_pdf($x, $nu)

This function computes the probability density p($x) at $x for a tdistribution with nu degrees of freedom, using the formula given above.
Laplace
 gsl_ran_laplace($r, $a)

This function returns a random variate from the Laplace distribution with width $a. The distribution is, p(x) dx = {1 \over 2 a} \exp(x/a) dx for \infty < x < \infty.
 gsl_ran_laplace_pdf($x, $a)

This function computes the probability density p($x) at $x for a Laplace distribution with width $a, using the formula given above.
Levy
 gsl_ran_levy($r, $c, $alpha)

This function returns a random variate from the Levy symmetric stable distribution with scale $c and exponent $alpha. The symmetric stable probability distribution is defined by a fourier transform, p(x) = {1 \over 2 \pi} \int_{\infty}^{+\infty} dt \exp(it x  c t^alpha) There is no explicit solution for the form of p(x) and the library does not define a corresponding pdf function. For \alpha = 1 the distribution reduces to the Cauchy distribution. For \alpha = 2 it is a Gaussian distribution with \sigma = \sqrt{2} c. For \alpha < 1 the tails of the distribution become extremely wide. The algorithm only works for 0 < alpha <= 2. $r is a gsl_rng structure
 gsl_ran_levy_skew($r, $c, $alpha, $beta)

This function returns a random variate from the Levy skew stable distribution with scale $c, exponent $alpha and skewness parameter $beta. The skewness parameter must lie in the range [1,1]. The Levy skew stable probability distribution is defined by a fourier transform, p(x) = {1 \over 2 \pi} \int_{\infty}^{+\infty} dt \exp(it x  c t^alpha (1i beta sign(t) tan(pi alpha/2))) When \alpha = 1 the term \tan(\pi \alpha/2) is replaced by (2/\pi)\logt. There is no explicit solution for the form of p(x) and the library does not define a corresponding pdf function. For $alpha = 2 the distribution reduces to a Gaussian distribution with $sigma = sqrt(2) $c and the skewness parameter has no effect. For $alpha < 1 the tails of the distribution become extremely wide. The symmetric distribution corresponds to $beta = 0. The algorithm only works for 0 < $alpha <= 2. The Levy alphastable distributions have the property that if N alphastable variates are drawn from the distribution p(c, \alpha, \beta) then the sum Y = X_1 + X_2 + \dots + X_N will also be distributed as an alphastable variate, p(N^(1/\alpha) c, \alpha, \beta). $r is a gsl_rng structure
Weibull
 gsl_ran_weibull($r, $scale, $exponent)

This function returns a random variate from the Weibull distribution with $scale and $exponent (aka scale). The distribution function is
p(x) dx = {$exponent \over $scale^$exponent} x^{$exponent1} \exp((x/$scale)^$exponent) dx
for x >= 0. $r is a gsl_rng structure
 gsl_ran_weibull_pdf($x, $scale, $exponent)

This function computes the probability density p($x) at $x for a Weibull distribution with $scale and $exponent, using the formula given above.
Spherical Vector
 gsl_ran_dir_2d($r)

This function returns two values. The first is $x and the second is $y of a random direction vector v = ($x,$y) in two dimensions. The vector is normalized such that v^2 = $x^2 + $y^2 = 1. $r is a gsl_rng structure
 gsl_ran_dir_2d_trig_method($r)

This function returns two values. The first is $x and the second is $y of a random direction vector v = ($x,$y) in two dimensions. The vector is normalized such that v^2 = $x^2 + $y^2 = 1. $r is a gsl_rng structure
 gsl_ran_dir_3d($r)

This function returns three values. The first is $x, the second $y and the third $z of a random direction vector v = ($x,$y,$z) in three dimensions. The vector is normalized such that v^2 = x^2 + y^2 + z^2 = 1. The method employed is due to Robert E. Knop (CACM 13, 326 (1970)), and explained in Knuth, v2, 3rd ed, p136. It uses the surprising fact that the distribution projected along any axis is actually uniform (this is only true for 3 dimensions).
 gsl_ran_dir_nd (Not yet implemented )

This function returns a random direction vector v = (x_1,x_2,...,x_n) in n dimensions. The vector is normalized such that
v^2 = x_1^2 + x_2^2 + ... + x_n^2 = 1.
The method uses the fact that a multivariate Gaussian distribution is spherically symmetric. Each component is generated to have a Gaussian distribution, and then the components are normalized. The method is described by Knuth, v2, 3rd ed, p135136, and attributed to G. W. Brown, Modern Mathematics for the Engineer (1956).
Shuffling and Sampling
 gsl_ran_shuffle

* Not yet implemented *
 gsl_ran_choose

* Not yet implemented * Sample without replacement
 gsl_ran_sample

* Not yet implemented * Sample with replacement
 gsl_ran_discrete_preproc
 gsl_ran_discrete($r, $g)

After gsl_ran_discrete_preproc has been called, you use this function to get the discrete random numbers. $r is a gsl_rng structure and $g is a gsl_ran_discrete structure
 gsl_ran_discrete_pdf($k, $g)

Returns the probability P[$k] of observing the variable $k. Since P[$k] is not stored as part of the lookup table, it must be recomputed; this computation takes O(K), so if K is large and you care about the original array P[$k] used to create the lookup table, then you should just keep this original array P[$k] around. $r is a gsl_rng structure and $g is a gsl_ran_discrete structure
 gsl_ran_discrete_free($g)

Deallocates the gsl_ran_discrete pointed to by g.
You have to add the functions you want to use inside the qw /put_funtion_here /.
You can also write use Math::GSL::Randist qw/:all/; to use all avaible functions of the module.
Other tags are also avaible, here is a complete list of all tags for this module :
 logarithmic
 choose
 exponential
 gumbel1
 exppow
 sample
 logistic
 gaussian
 poisson
 binomial
 fdist
 chisq
 gamma
 hypergeometric
 dirichlet
 negative
 flat
 geometric
 discrete
 tdist
 ugaussian
 rayleigh
 dir
 pascal
 gumbel2
 shuffle
 landau
 bernoulli
 weibull
 multinomial
 beta
 lognormal
 laplace
 erlang
 cauchy
 levy
 bivariate
 pareto
For example the beta tag contains theses functions : gsl_ran_beta, gsl_ran_beta_pdf.
For more informations on the functions, we refer you to the GSL offcial documentation: http://www.gnu.org/software/gsl/manual/html_node/
You might also want to write
use Math::GSL::RNG qw/:all/;
since a lot of the functions of Math::GSL::Randist take as argument a structure that is created by Math::GSL::RNG. Refer to Math::GSL::RNG documentation to see how to create such a structure.
Math::GSL::CDF also contains a structure named gsl_ran_discrete_t. An example is given in the EXAMPLES part on how to use the function related to this structure.
EXAMPLES
use Math::GSL::Randist qw/:all/;
print gsl_ran_exponential_pdf(5,2) . "\n";
use Math::GSL::Randist qw/:all/;
my $x = Math::GSL::gsl_ran_discrete_t::new;
AUTHORS
Jonathan "Duke" Leto <jonathan@leto.net> and Thierry Moisan <thierry.moisan@gmail.com>
COPYRIGHT AND LICENSE
Copyright (C) 20082013 Jonathan "Duke" Leto and Thierry Moisan
This program is free software; you can redistribute it and/or modify it under the same terms as Perl itself.